summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Documentation/admin-guide/kernel-parameters.txt6
-rw-r--r--arch/arm64/Kconfig1
-rw-r--r--arch/arm64/include/asm/kvm_arm.h1
-rw-r--r--arch/arm64/include/asm/kvm_asm.h48
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h5
-rw-r--r--arch/arm64/include/asm/kvm_host.h3
-rw-r--r--arch/arm64/include/asm/kvm_hyp.h5
-rw-r--r--arch/arm64/include/asm/sysreg.h3
-rw-r--r--arch/arm64/kernel/smp.c3
-rw-r--r--arch/arm64/kvm/Kconfig10
-rw-r--r--arch/arm64/kvm/arm.c94
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/fault.h75
-rw-r--r--arch/arm64/kvm/hyp/include/hyp/switch.h235
-rw-r--r--arch/arm64/kvm/hyp/include/nvhe/fixed_config.h200
-rw-r--r--arch/arm64/kvm/hyp/include/nvhe/trap_handler.h2
-rw-r--r--arch/arm64/kvm/hyp/nvhe/Makefile2
-rw-r--r--arch/arm64/kvm/hyp/nvhe/host.S26
-rw-r--r--arch/arm64/kvm/hyp/nvhe/hyp-main.c48
-rw-r--r--arch/arm64/kvm/hyp/nvhe/mem_protect.c11
-rw-r--r--arch/arm64/kvm/hyp/nvhe/pkvm.c185
-rw-r--r--arch/arm64/kvm/hyp/nvhe/setup.c3
-rw-r--r--arch/arm64/kvm/hyp/nvhe/switch.c99
-rw-r--r--arch/arm64/kvm/hyp/nvhe/sys_regs.c487
-rw-r--r--arch/arm64/kvm/hyp/vgic-v3-sr.c22
-rw-r--r--arch/arm64/kvm/hyp/vhe/switch.c16
-rw-r--r--arch/arm64/kvm/mmu.c2
-rw-r--r--arch/arm64/kvm/pmu-emul.c2
-rw-r--r--arch/arm64/kvm/reset.c2
-rw-r--r--arch/arm64/kvm/sys_regs.c41
-rw-r--r--arch/arm64/kvm/vgic/vgic-init.c2
-rw-r--r--arch/arm64/kvm/vgic/vgic-irqfd.c2
-rw-r--r--arch/arm64/kvm/vgic/vgic-its.c18
-rw-r--r--arch/arm64/kvm/vgic/vgic-kvm-device.c25
-rw-r--r--arch/arm64/kvm/vgic/vgic-mmio-v3.c8
-rw-r--r--arch/arm64/kvm/vgic/vgic-v3.c27
-rw-r--r--arch/arm64/kvm/vgic/vgic-v4.c2
-rw-r--r--arch/arm64/kvm/vgic/vgic.h5
-rw-r--r--tools/arch/arm64/include/asm/sysreg.h1296
-rw-r--r--tools/testing/selftests/kvm/.gitignore1
-rw-r--r--tools/testing/selftests/kvm/Makefile3
-rw-r--r--tools/testing/selftests/kvm/aarch64/arch_timer.c479
-rw-r--r--tools/testing/selftests/kvm/aarch64/debug-exceptions.c30
-rw-r--r--tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c2
-rw-r--r--tools/testing/selftests/kvm/aarch64/vgic_init.c369
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/arch_timer.h142
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/delay.h25
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/gic.h21
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/processor.h90
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/spinlock.h13
-rw-r--r--tools/testing/selftests/kvm/include/aarch64/vgic.h20
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h2
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic.c95
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic_private.h21
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic_v3.c240
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/gic_v3.h70
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/processor.c24
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/spinlock.c27
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/vgic.c70
58 files changed, 4337 insertions, 429 deletions
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 91ba391f9b32..12b336bc1fe9 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2365,6 +2365,8 @@
kvm-arm.mode=
[KVM,ARM] Select one of KVM/arm64's modes of operation.
+ none: Forcefully disable KVM.
+
nvhe: Standard nVHE-based mode, without support for
protected guests.
@@ -2372,7 +2374,9 @@
state is kept private from the host.
Not valid if the kernel is running in EL2.
- Defaults to VHE/nVHE based on hardware support.
+ Defaults to VHE/nVHE based on hardware support. Setting
+ mode to "protected" will disable kexec and hibernation
+ for the host.
kvm-arm.vgic_v3_group0_trap=
[KVM,ARM] Trap guest accesses to GICv3 group-0
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 5c7ae4c3954b..0d921d21fd35 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -186,6 +186,7 @@ config ARM64
select HAVE_GCC_PLUGINS
select HAVE_HW_BREAKPOINT if PERF_EVENTS
select HAVE_IRQ_TIME_ACCOUNTING
+ select HAVE_KVM
select HAVE_NMI
select HAVE_PATA_PLATFORM
select HAVE_PERF_EVENTS
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 327120c0089f..a39fcf318c77 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -295,6 +295,7 @@
#define MDCR_EL2_HPMFZO (UL(1) << 29)
#define MDCR_EL2_MTPME (UL(1) << 28)
#define MDCR_EL2_TDCC (UL(1) << 27)
+#define MDCR_EL2_HLP (UL(1) << 26)
#define MDCR_EL2_HCCD (UL(1) << 23)
#define MDCR_EL2_TTRF (UL(1) << 19)
#define MDCR_EL2_HPMD (UL(1) << 17)
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index e86045ac43ba..0167f3702c61 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -44,31 +44,39 @@
#define KVM_HOST_SMCCC_FUNC(name) KVM_HOST_SMCCC_ID(__KVM_HOST_SMCCC_FUNC_##name)
#define __KVM_HOST_SMCCC_FUNC___kvm_hyp_init 0
-#define __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run 1
-#define __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context 2
-#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa 3
-#define __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid 4
-#define __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context 5
-#define __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff 6
-#define __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs 7
-#define __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config 8
-#define __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr 9
-#define __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr 10
-#define __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs 11
-#define __KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2 12
-#define __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs 13
-#define __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs 14
-#define __KVM_HOST_SMCCC_FUNC___pkvm_init 15
-#define __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp 16
-#define __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping 17
-#define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18
-#define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19
-#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 20
#ifndef __ASSEMBLY__
#include <linux/mm.h>
+enum __kvm_host_smccc_func {
+ /* Hypercalls available only prior to pKVM finalisation */
+ /* __KVM_HOST_SMCCC_FUNC___kvm_hyp_init */
+ __KVM_HOST_SMCCC_FUNC___kvm_get_mdcr_el2 = __KVM_HOST_SMCCC_FUNC___kvm_hyp_init + 1,
+ __KVM_HOST_SMCCC_FUNC___pkvm_init,
+ __KVM_HOST_SMCCC_FUNC___pkvm_create_private_mapping,
+ __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector,
+ __KVM_HOST_SMCCC_FUNC___kvm_enable_ssbs,
+ __KVM_HOST_SMCCC_FUNC___vgic_v3_init_lrs,
+ __KVM_HOST_SMCCC_FUNC___vgic_v3_get_gic_config,
+ __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize,
+
+ /* Hypercalls available after pKVM finalisation */
+ __KVM_HOST_SMCCC_FUNC___pkvm_host_share_hyp,
+ __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc,
+ __KVM_HOST_SMCCC_FUNC___kvm_vcpu_run,
+ __KVM_HOST_SMCCC_FUNC___kvm_flush_vm_context,
+ __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid_ipa,
+ __KVM_HOST_SMCCC_FUNC___kvm_tlb_flush_vmid,
+ __KVM_HOST_SMCCC_FUNC___kvm_flush_cpu_context,
+ __KVM_HOST_SMCCC_FUNC___kvm_timer_set_cntvoff,
+ __KVM_HOST_SMCCC_FUNC___vgic_v3_read_vmcr,
+ __KVM_HOST_SMCCC_FUNC___vgic_v3_write_vmcr,
+ __KVM_HOST_SMCCC_FUNC___vgic_v3_save_aprs,
+ __KVM_HOST_SMCCC_FUNC___vgic_v3_restore_aprs,
+ __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_init_traps,
+};
+
#define DECLARE_KVM_VHE_SYM(sym) extern char sym[]
#define DECLARE_KVM_NVHE_SYM(sym) extern char kvm_nvhe_sym(sym)[]
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index fd418955e31e..f4871e47b2d0 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -396,7 +396,10 @@ static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
if (vcpu_mode_is_32bit(vcpu))
return !!(*vcpu_cpsr(vcpu) & PSR_AA32_E_BIT);
- return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & (1 << 25));
+ if (vcpu_mode_priv(vcpu))
+ return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & SCTLR_ELx_EE);
+ else
+ return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & SCTLR_EL1_E0E);
}
static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f8be56d5342b..d0221fb69a60 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -58,6 +58,7 @@
enum kvm_mode {
KVM_MODE_DEFAULT,
KVM_MODE_PROTECTED,
+ KVM_MODE_NONE,
};
enum kvm_mode kvm_get_mode(void);
@@ -780,6 +781,8 @@ static inline bool kvm_vm_is_protected(struct kvm *kvm)
return false;
}
+void kvm_init_protected_traps(struct kvm_vcpu *vcpu);
+
int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature);
bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 657d0c94cf82..5afd14ab15b9 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -115,7 +115,12 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt);
#endif
+extern u64 kvm_nvhe_sym(id_aa64pfr0_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64pfr1_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64isar0_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64isar1_el1_sys_val);
extern u64 kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val);
extern u64 kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val);
+extern u64 kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val);
#endif /* __ARM64_KVM_HYP_H__ */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index b268082d67ed..9412a645a1c0 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1152,6 +1152,7 @@
#define ICH_HCR_TC (1 << 10)
#define ICH_HCR_TALL0 (1 << 11)
#define ICH_HCR_TALL1 (1 << 12)
+#define ICH_HCR_TDIR (1 << 14)
#define ICH_HCR_EOIcount_SHIFT 27
#define ICH_HCR_EOIcount_MASK (0x1f << ICH_HCR_EOIcount_SHIFT)
@@ -1184,6 +1185,8 @@
#define ICH_VTR_SEIS_MASK (1 << ICH_VTR_SEIS_SHIFT)
#define ICH_VTR_A3V_SHIFT 21
#define ICH_VTR_A3V_MASK (1 << ICH_VTR_A3V_SHIFT)
+#define ICH_VTR_TDS_SHIFT 19
+#define ICH_VTR_TDS_MASK (1 << ICH_VTR_TDS_SHIFT)
#define ARM64_FEATURE_FIELD_BITS 4
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 6f6ff072acbd..44369b99a57e 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -1128,5 +1128,6 @@ bool cpus_are_stuck_in_kernel(void)
{
bool smp_spin_tables = (num_possible_cpus() > 1 && !have_cpu_die());
- return !!cpus_stuck_in_kernel || smp_spin_tables;
+ return !!cpus_stuck_in_kernel || smp_spin_tables ||
+ is_protected_kvm_enabled();
}
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index d7eec0b43744..8ffcbe29395e 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -4,6 +4,7 @@
#
source "virt/lib/Kconfig"
+source "virt/kvm/Kconfig"
menuconfig VIRTUALIZATION
bool "Virtualization"
@@ -19,7 +20,7 @@ if VIRTUALIZATION
menuconfig KVM
bool "Kernel-based Virtual Machine (KVM) support"
- depends on OF
+ depends on HAVE_KVM
select MMU_NOTIFIER
select PREEMPT_NOTIFIERS
select HAVE_KVM_CPU_RELAX_INTERCEPT
@@ -43,12 +44,9 @@ menuconfig KVM
If unsure, say N.
-if KVM
-
-source "virt/kvm/Kconfig"
-
config NVHE_EL2_DEBUG
bool "Debug mode for non-VHE EL2 object"
+ depends on KVM
help
Say Y here to enable the debug mode for the non-VHE KVM EL2 object.
Failure reports will BUG() in the hypervisor. This is intended for
@@ -56,6 +54,4 @@ config NVHE_EL2_DEBUG
If unsure, say N.
-endif # KVM
-
endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index fe102cd2e518..24a1e86d7128 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -291,10 +291,12 @@ long kvm_arch_dev_ioctl(struct file *filp,
struct kvm *kvm_arch_alloc_vm(void)
{
+ size_t sz = sizeof(struct kvm);
+
if (!has_vhe())
- return kzalloc(sizeof(struct kvm), GFP_KERNEL);
+ return kzalloc(sz, GFP_KERNEL_ACCOUNT);
- return vzalloc(sizeof(struct kvm));
+ return __vmalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_HIGHMEM | __GFP_ZERO);
}
void kvm_arch_free_vm(struct kvm *kvm)
@@ -620,6 +622,14 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
ret = kvm_arm_pmu_v3_enable(vcpu);
+ /*
+ * Initialize traps for protected VMs.
+ * NOTE: Move to run in EL2 directly, rather than via a hypercall, once
+ * the code is in place for first run initialization at EL2.
+ */
+ if (kvm_vm_is_protected(kvm))
+ kvm_call_hyp_nvhe(__pkvm_vcpu_init_traps, vcpu);
+
return ret;
}
@@ -1579,25 +1589,33 @@ static void cpu_set_hyp_vector(void)
kvm_call_hyp_nvhe(__pkvm_cpu_set_vector, data->slot);
}
-static void cpu_hyp_reinit(void)
+static void cpu_hyp_init_context(void)
{
kvm_init_host_cpu_context(&this_cpu_ptr_hyp_sym(kvm_host_data)->host_ctxt);
- cpu_hyp_reset();
-
- if (is_kernel_in_hyp_mode())
- kvm_timer_init_vhe();
- else
+ if (!is_kernel_in_hyp_mode())
cpu_init_hyp_mode();
+}
+static void cpu_hyp_init_features(void)
+{
cpu_set_hyp_vector();
-
kvm_arm_init_debug();
+ if (is_kernel_in_hyp_mode())
+ kvm_timer_init_vhe();
+
if (vgic_present)
kvm_vgic_init_cpu_hardware();
}
+static void cpu_hyp_reinit(void)
+{
+ cpu_hyp_reset();
+ cpu_hyp_init_context();
+ cpu_hyp_init_features();
+}
+
static void _kvm_arch_hardware_enable(void *discard)
{
if (!__this_cpu_read(kvm_arm_hardware_enabled)) {
@@ -1788,10 +1806,17 @@ static int do_pkvm_init(u32 hyp_va_bits)
int ret;
preempt_disable();
- hyp_install_host_vector();
+ cpu_hyp_init_context();
ret = kvm_call_hyp_nvhe(__pkvm_init, hyp_mem_base, hyp_mem_size,
num_possible_cpus(), kern_hyp_va(per_cpu_base),
hyp_va_bits);
+ cpu_hyp_init_features();
+
+ /*
+ * The stub hypercalls are now disabled, so set our local flag to
+ * prevent a later re-init attempt in kvm_arch_hardware_enable().
+ */
+ __this_cpu_write(kvm_arm_hardware_enabled, 1);
preempt_enable();
return ret;
@@ -1802,8 +1827,13 @@ static int kvm_hyp_init_protection(u32 hyp_va_bits)
void *addr = phys_to_virt(hyp_mem_base);
int ret;
+ kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1);
+ kvm_nvhe_sym(id_aa64pfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1);
+ kvm_nvhe_sym(id_aa64isar0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR0_EL1);
+ kvm_nvhe_sym(id_aa64isar1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1);
kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
+ kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1);
ret = create_hyp_mappings(addr, addr + hyp_mem_size, PAGE_HYP);
if (ret)
@@ -1971,9 +2001,25 @@ out_err:
return err;
}
-static void _kvm_host_prot_finalize(void *discard)
+static void _kvm_host_prot_finalize(void *arg)
{
- WARN_ON(kvm_call_hyp_nvhe(__pkvm_prot_finalize));
+ int *err = arg;
+
+ if (WARN_ON(kvm_call_hyp_nvhe(__pkvm_prot_finalize)))
+ WRITE_ONCE(*err, -EINVAL);
+}
+
+static int pkvm_drop_host_privileges(void)
+{
+ int ret = 0;
+
+ /*
+ * Flip the static key upfront as that may no longer be possible
+ * once the host stage 2 is installed.
+ */
+ static_branch_enable(&kvm_protected_mode_initialized);
+ on_each_cpu(_kvm_host_prot_finalize, &ret, 1);
+ return ret;
}
static int finalize_hyp_mode(void)
@@ -1987,15 +2033,7 @@ static int finalize_hyp_mode(void)
* None of other sections should ever be introspected.
*/
kmemleak_free_part(__hyp_bss_start, __hyp_bss_end - __hyp_bss_start);
-
- /*
- * Flip the static key upfront as that may no longer be possible
- * once the host stage 2 is installed.
- */
- static_branch_enable(&kvm_protected_mode_initialized);
- on_each_cpu(_kvm_host_prot_finalize, NULL, 1);
-
- return 0;
+ return pkvm_drop_host_privileges();
}
struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
@@ -2064,6 +2102,11 @@ int kvm_arch_init(void *opaque)
return -ENODEV;
}
+ if (kvm_get_mode() == KVM_MODE_NONE) {
+ kvm_info("KVM disabled from command line\n");
+ return -ENODEV;
+ }
+
in_hyp_mode = is_kernel_in_hyp_mode();
if (cpus_have_final_cap(ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE) ||
@@ -2137,8 +2180,15 @@ static int __init early_kvm_mode_cfg(char *arg)
return 0;
}
- if (strcmp(arg, "nvhe") == 0 && !WARN_ON(is_kernel_in_hyp_mode()))
+ if (strcmp(arg, "nvhe") == 0 && !WARN_ON(is_kernel_in_hyp_mode())) {
+ kvm_mode = KVM_MODE_DEFAULT;
+ return 0;
+ }
+
+ if (strcmp(arg, "none") == 0) {
+ kvm_mode = KVM_MODE_NONE;
return 0;
+ }
return -EINVAL;
}
diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h
new file mode 100644
index 000000000000..1b8a2dcd712f
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/hyp/fault.h
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2015 - ARM Ltd
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ */
+
+#ifndef __ARM64_KVM_HYP_FAULT_H__
+#define __ARM64_KVM_HYP_FAULT_H__
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_emulate.h>
+#include <asm/kvm_hyp.h>
+#include <asm/kvm_mmu.h>
+
+static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
+{
+ u64 par, tmp;
+
+ /*
+ * Resolve the IPA the hard way using the guest VA.
+ *
+ * Stage-1 translation already validated the memory access
+ * rights. As such, we can use the EL1 translation regime, and
+ * don't have to distinguish between EL0 and EL1 access.
+ *
+ * We do need to save/restore PAR_EL1 though, as we haven't
+ * saved the guest context yet, and we may return early...
+ */
+ par = read_sysreg_par();
+ if (!__kvm_at("s1e1r", far))
+ tmp = read_sysreg_par();
+ else
+ tmp = SYS_PAR_EL1_F; /* back to the guest */
+ write_sysreg(par, par_el1);
+
+ if (unlikely(tmp & SYS_PAR_EL1_F))
+ return false; /* Translation failed, back to guest */
+
+ /* Convert PAR to HPFAR format */
+ *hpfar = PAR_TO_HPFAR(tmp);
+ return true;
+}
+
+static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
+{
+ u64 hpfar, far;
+
+ far = read_sysreg_el2(SYS_FAR);
+
+ /*
+ * The HPFAR can be invalid if the stage 2 fault did not
+ * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
+ * bit is clear) and one of the two following cases are true:
+ * 1. The fault was due to a permission fault
+ * 2. The processor carries errata 834220
+ *
+ * Therefore, for all non S1PTW faults where we either have a
+ * permission fault or the errata workaround is enabled, we
+ * resolve the IPA using the AT instruction.
+ */
+ if (!(esr & ESR_ELx_S1PTW) &&
+ (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
+ (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+ if (!__translate_far_to_hpfar(far, &hpfar))
+ return false;
+ } else {
+ hpfar = read_sysreg(hpfar_el2);
+ }
+
+ fault->far_el2 = far;
+ fault->hpfar_el2 = hpfar;
+ return true;
+}
+
+#endif
diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h
index a0e78a6027be..c6e98c7e918b 100644
--- a/arch/arm64/kvm/hyp/include/hyp/switch.h
+++ b/arch/arm64/kvm/hyp/include/hyp/switch.h
@@ -8,6 +8,7 @@
#define __ARM64_KVM_HYP_SWITCH_H__
#include <hyp/adjust_pc.h>
+#include <hyp/fault.h>
#include <linux/arm-smccc.h>
#include <linux/kvm_host.h>
@@ -133,78 +134,9 @@ static inline void ___deactivate_traps(struct kvm_vcpu *vcpu)
}
}
-static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar)
-{
- u64 par, tmp;
-
- /*
- * Resolve the IPA the hard way using the guest VA.
- *
- * Stage-1 translation already validated the memory access
- * rights. As such, we can use the EL1 translation regime, and
- * don't have to distinguish between EL0 and EL1 access.
- *
- * We do need to save/restore PAR_EL1 though, as we haven't
- * saved the guest context yet, and we may return early...
- */
- par = read_sysreg_par();
- if (!__kvm_at("s1e1r", far))
- tmp = read_sysreg_par();
- else
- tmp = SYS_PAR_EL1_F; /* back to the guest */
- write_sysreg(par, par_el1);
-
- if (unlikely(tmp & SYS_PAR_EL1_F))
- return false; /* Translation failed, back to guest */
-
- /* Convert PAR to HPFAR format */
- *hpfar = PAR_TO_HPFAR(tmp);
- return true;
-}
-
-static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault)
-{
- u64 hpfar, far;
-
- far = read_sysreg_el2(SYS_FAR);
-
- /*
- * The HPFAR can be invalid if the stage 2 fault did not
- * happen during a stage 1 page table walk (the ESR_EL2.S1PTW
- * bit is clear) and one of the two following cases are true:
- * 1. The fault was due to a permission fault
- * 2. The processor carries errata 834220
- *
- * Therefore, for all non S1PTW faults where we either have a
- * permission fault or the errata workaround is enabled, we
- * resolve the IPA using the AT instruction.
- */
- if (!(esr & ESR_ELx_S1PTW) &&
- (cpus_have_final_cap(ARM64_WORKAROUND_834220) ||
- (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
- if (!__translate_far_to_hpfar(far, &hpfar))
- return false;
- } else {
- hpfar = read_sysreg(hpfar_el2);
- }
-
- fault->far_el2 = far;
- fault->hpfar_el2 = hpfar;
- return true;
-}
-
static inline bool __populate_fault_info(struct kvm_vcpu *vcpu)
{
- u8 ec;
- u64 esr;
-
- esr = vcpu->arch.fault.esr_el2;
- ec = ESR_ELx_EC(esr);
-
- if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW)
- return true;
-
- return __get_fault_info(esr, &vcpu->arch.fault);
+ return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault);
}
static inline void __hyp_sve_save_host(struct kvm_vcpu *vcpu)
@@ -225,8 +157,13 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu)
write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR);
}
-/* Check for an FPSIMD/SVE trap and handle as appropriate */
-static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
+/*
+ * We trap the first access to the FP/SIMD to save the host context and
+ * restore the guest context lazily.
+ * If FP/SIMD is not implemented, handle the trap and inject an undefined
+ * instruction exception to the guest. Similarly for trapped SVE accesses.
+ */
+static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
{
bool sve_guest, sve_host;
u8 esr_ec;
@@ -244,9 +181,6 @@ static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu)
}
esr_ec = kvm_vcpu_trap_get_class(vcpu);
- if (esr_ec != ESR_ELx_EC_FP_ASIMD &&
- esr_ec != ESR_ELx_EC_SVE)
- return false;
/* Don't handle SVE traps for non-SVE vcpus here: */
if (!sve_guest && esr_ec != ESR_ELx_EC_FP_ASIMD)
@@ -348,14 +282,6 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu)
static inline bool esr_is_ptrauth_trap(u32 esr)
{
- u32 ec = ESR_ELx_EC(esr);
-
- if (ec == ESR_ELx_EC_PAC)
- return true;
-
- if (ec != ESR_ELx_EC_SYS64)
- return false;
-
switch (esr_sys64_to_sysreg(esr)) {
case SYS_APIAKEYLO_EL1:
case SYS_APIAKEYHI_EL1:
@@ -384,13 +310,12 @@ static inline bool esr_is_ptrauth_trap(u32 esr)
DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
-static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
+static bool kvm_hyp_handle_ptrauth(struct kvm_vcpu *vcpu, u64 *exit_code)
{
struct kvm_cpu_context *ctxt;
u64 val;
- if (!vcpu_has_ptrauth(vcpu) ||
- !esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
+ if (!vcpu_has_ptrauth(vcpu))
return false;
ctxt = this_cpu_ptr(&kvm_hyp_ctxt);
@@ -409,6 +334,90 @@ static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu)
return true;
}
+static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
+ handle_tx2_tvm(vcpu))
+ return true;
+
+ if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+ __vgic_v3_perform_cpuif_access(vcpu) == 1)
+ return true;
+
+ if (esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu)))
+ return kvm_hyp_handle_ptrauth(vcpu, exit_code);
+
+ return false;
+}
+
+static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
+ __vgic_v3_perform_cpuif_access(vcpu) == 1)
+ return true;
+
+ return false;
+}
+
+static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ if (!__populate_fault_info(vcpu))
+ return true;
+
+ return false;
+}
+
+static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ if (!__populate_fault_info(vcpu))
+ return true;
+
+ if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
+ bool valid;
+
+ valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
+ kvm_vcpu_dabt_isvalid(vcpu) &&
+ !kvm_vcpu_abt_issea(vcpu) &&
+ !kvm_vcpu_abt_iss1tw(vcpu);
+
+ if (valid) {
+ int ret = __vgic_v2_perform_cpuif_access(vcpu);
+
+ if (ret == 1)
+ return true;
+
+ /* Promote an illegal access to an SError.*/
+ if (ret == -1)
+ *exit_code = ARM_EXCEPTION_EL1_SERROR;
+ }
+ }
+
+ return false;
+}
+
+typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *);
+
+static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu);
+
+/*
+ * Allow the hypervisor to handle the exit with an exit handler if it has one.
+ *
+ * Returns true if the hypervisor handled the exit, and control should go back
+ * to the guest, or false if it hasn't.
+ */
+static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu);
+ exit_handler_fn fn;
+
+ fn = handlers[kvm_vcpu_trap_get_class(vcpu)];
+
+ if (fn)
+ return fn(vcpu, exit_code);
+
+ return false;
+}
+
/*
* Return true when we were able to fixup the guest exit and should return to
* the guest, false when we should restore the host state and return to the
@@ -443,59 +452,9 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
if (*exit_code != ARM_EXCEPTION_TRAP)
goto exit;
- if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) &&
- kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 &&
- handle_tx2_tvm(vcpu))
+ /* Check if there's an exit handler and allow it to handle the exit. */
+ if (kvm_hyp_handle_exit(vcpu, exit_code))
goto guest;
-
- /*
- * We trap the first access to the FP/SIMD to save the host context
- * and restore the guest context lazily.
- * If FP/SIMD is not implemented, handle the trap and inject an
- * undefined instruction exception to the guest.
- * Similarly for trapped SVE accesses.
- */
- if (__hyp_handle_fpsimd(vcpu))
- goto guest;
-
- if (__hyp_handle_ptrauth(vcpu))
- goto guest;
-
- if (!__populate_fault_info(vcpu))
- goto guest;
-
- if (static_branch_unlikely(&vgic_v2_cpuif_trap)) {
- bool valid;
-
- valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW &&
- kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT &&
- kvm_vcpu_dabt_isvalid(vcpu) &&
- !kvm_vcpu_abt_issea(vcpu) &&
- !kvm_vcpu_abt_iss1tw(vcpu);
-
- if (valid) {
- int ret = __vgic_v2_perform_cpuif_access(vcpu);
-
- if (ret == 1)
- goto guest;
-
- /* Promote an illegal access to an SError.*/
- if (ret == -1)
- *exit_code = ARM_EXCEPTION_EL1_SERROR;
-
- goto exit;
- }
- }
-
- if (static_branch_unlikely(&vgic_v3_cpuif_trap) &&
- (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 ||
- kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) {
- int ret = __vgic_v3_perform_cpuif_access(vcpu);
-
- if (ret == 1)
- goto guest;
- }
-
exit:
/* Return to the host kernel and handle the exit */
return false;
diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
new file mode 100644
index 000000000000..eea1f6a53723
--- /dev/null
+++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h
@@ -0,0 +1,200 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Google LLC
+ * Author: Fuad Tabba <tabba@google.com>
+ */
+
+#ifndef __ARM64_KVM_FIXED_CONFIG_H__
+#define __ARM64_KVM_FIXED_CONFIG_H__
+
+#include <asm/sysreg.h>
+
+/*
+ * This file contains definitions for features to be allowed or restricted for
+ * guest virtual machines, depending on the mode KVM is running in and on the
+ * type of guest that is running.
+ *
+ * The ALLOW masks represent a bitmask of feature fields that are allowed
+ * without any restrictions as long as they are supported by the system.
+ *
+ * The RESTRICT_UNSIGNED masks, if present, represent unsigned fields for
+ * features that are restricted to support at most the specified feature.
+ *
+ * If a feature field is not present in either, than it is not supported.
+ *
+ * The approach taken for protected VMs is to allow features that are:
+ * - Needed by common Linux distributions (e.g., floating point)
+ * - Trivial to support, e.g., supporting the feature does not introduce or
+ * require tracking of additional state in KVM
+ * - Cannot be trapped or prevent the guest from using anyway
+ */
+
+/*
+ * Allow for protected VMs:
+ * - Floating-point and Advanced SIMD
+ * - Data Independent Timing
+ */
+#define PVM_ID_AA64PFR0_ALLOW (\
+ ARM64_FEATURE_MASK(ID_AA64PFR0_FP) | \
+ ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD) | \
+ ARM64_FEATURE_MASK(ID_AA64PFR0_DIT) \
+ )
+
+/*
+ * Restrict to the following *unsigned* features for protected VMs:
+ * - AArch64 guests only (no support for AArch32 guests):
+ * AArch32 adds complexity in trap handling, emulation, condition codes,
+ * etc...
+ * - RAS (v1)
+ * Supported by KVM
+ */
+#define PVM_ID_AA64PFR0_RESTRICT_UNSIGNED (\
+ FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL0), ID_AA64PFR0_ELx_64BIT_ONLY) | \
+ FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1), ID_AA64PFR0_ELx_64BIT_ONLY) | \
+ FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL2), ID_AA64PFR0_ELx_64BIT_ONLY) | \
+ FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL3), ID_AA64PFR0_ELx_64BIT_ONLY) | \
+ FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_RAS), ID_AA64PFR0_RAS_V1) \
+ )
+
+/*
+ * Allow for protected VMs:
+ * - Branch Target Identification
+ * - Speculative Store Bypassing
+ */
+#define PVM_ID_AA64PFR1_ALLOW (\
+ ARM64_FEATURE_MASK(ID_AA64PFR1_BT) | \
+ ARM64_FEATURE_MASK(ID_AA64PFR1_SSBS) \
+ )
+
+/*
+ * Allow for protected VMs:
+ * - Mixed-endian
+ * - Distinction between Secure and Non-secure Memory
+ * - Mixed-endian at EL0 only
+ * - Non-context synchronizing exception entry and exit
+ */
+#define PVM_ID_AA64MMFR0_ALLOW (\
+ ARM64_FEATURE_MASK(ID_AA64MMFR0_BIGENDEL) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR0_SNSMEM) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR0_BIGENDEL0) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR0_EXS) \
+ )
+
+/*
+ * Restrict to the following *unsigned* features for protected VMs:
+ * - 40-bit IPA
+ * - 16-bit ASID
+ */
+#define PVM_ID_AA64MMFR0_RESTRICT_UNSIGNED (\
+ FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64MMFR0_PARANGE), ID_AA64MMFR0_PARANGE_40) | \
+ FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64MMFR0_ASID), ID_AA64MMFR0_ASID_16) \
+ )
+
+/*
+ * Allow for protected VMs:
+ * - Hardware translation table updates to Access flag and Dirty state
+ * - Number of VMID bits from CPU
+ * - Hierarchical Permission Disables
+ * - Privileged Access Never
+ * - SError interrupt exceptions from speculative reads
+ * - Enhanced Translation Synchronization
+ */
+#define PVM_ID_AA64MMFR1_ALLOW (\
+ ARM64_FEATURE_MASK(ID_AA64MMFR1_HADBS) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR1_VMIDBITS) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR1_HPD) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR1_PAN) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR1_SPECSEI) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR1_ETS) \
+ )
+
+/*
+ * Allow for protected VMs:
+ * - Common not Private translations
+ * - User Access Override
+ * - IESB bit in the SCTLR_ELx registers
+ * - Unaligned single-copy atomicity and atomic functions
+ * - ESR_ELx.EC value on an exception by read access to feature ID space
+ * - TTL field in address operations.
+ * - Break-before-make sequences when changing translation block size
+ * - E0PDx mechanism
+ */
+#define PVM_ID_AA64MMFR2_ALLOW (\
+ ARM64_FEATURE_MASK(ID_AA64MMFR2_CNP) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR2_UAO) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR2_IESB) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR2_AT) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR2_IDS) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR2_TTL) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR2_BBM) | \
+ ARM64_FEATURE_MASK(ID_AA64MMFR2_E0PD) \
+ )
+
+/*
+ * No support for Scalable Vectors for protected VMs:
+ * Requires additional support from KVM, e.g., context-switching and
+ * trapping at EL2
+ */
+#define PVM_ID_AA64ZFR0_ALLOW (0ULL)
+
+/*
+ * No support for debug, including breakpoints, and watchpoints for protected
+ * VMs:
+ * The Arm architecture mandates support for at least the Armv8 debug
+ * architecture, which would include at least 2 hardware breakpoints and
+ * watchpoints. Providing that support to protected guests adds
+ * considerable state and complexity. Therefore, the reserved value of 0 is
+ * used for debug-related fields.
+ */
+#define PVM_ID_AA64DFR0_ALLOW (0ULL)
+#define PVM_ID_AA64DFR1_ALLOW (0ULL)
+
+/*
+ * No support for implementation defined features.
+ */
+#define PVM_ID_AA64AFR0_ALLOW (0ULL)
+#define PVM_ID_AA64AFR1_ALLOW (0ULL)
+
+/*
+ * No restrictions on instructions implemented in AArch64.
+ */
+#define PVM_ID_AA64ISAR0_ALLOW (\
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_AES) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA1) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA2) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_CRC32) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_ATOMICS) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_RDM) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA3) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_SM3) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_SM4) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_DP) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_FHM) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_TS) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_TLB) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR0_RNDR) \
+ )
+
+#define PVM_ID_AA64ISAR1_ALLOW (\
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_DPB) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_APA) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_API) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_JSCVT) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_FCMA) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_LRCPC) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_GPA) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_GPI) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_FRINTTS) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_SB) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_SPECRES) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_BF16) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_DGH) | \
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_I8MM) \
+ )
+
+u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id);
+bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code);
+bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code);
+int kvm_check_pvm_sysreg_table(void);
+
+#endif /* __ARM64_KVM_FIXED_CONFIG_H__ */
diff --git a/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h b/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h
index 1e6d995968a1..45a84f0ade04 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h
@@ -15,4 +15,6 @@
#define DECLARE_REG(type, name, ctxt, reg) \
type name = (type)cpu_reg(ctxt, (reg))
+void __pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu);
+
#endif /* __ARM64_KVM_NVHE_TRAP_HANDLER_H__ */
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index 8d741f71377f..c3c11974fa3b 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -14,7 +14,7 @@ lib-objs := $(addprefix ../../../lib/, $(lib-objs))
obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \
hyp-main.o hyp-smp.o psci-relay.o early_alloc.o stub.o page_alloc.o \
- cache.o setup.o mm.o mem_protect.o
+ cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o
obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
../fpsimd.o ../hyp-entry.o ../exception.o ../pgtable.o
obj-y += $(lib-objs)
diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S
index 4b652ffb591d..0c6116d34e18 100644
--- a/arch/arm64/kvm/hyp/nvhe/host.S
+++ b/arch/arm64/kvm/hyp/nvhe/host.S
@@ -110,17 +110,14 @@ SYM_FUNC_START(__hyp_do_panic)
b __host_enter_for_panic
SYM_FUNC_END(__hyp_do_panic)
-.macro host_el1_sync_vect
- .align 7
-.L__vect_start\@:
- stp x0, x1, [sp, #-16]!
- mrs x0, esr_el2
- lsr x0, x0, #ESR_ELx_EC_SHIFT
- cmp x0, #ESR_ELx_EC_HVC64
- b.ne __host_exit
-
+SYM_FUNC_START(__host_hvc)
ldp x0, x1, [sp] // Don't fixup the stack yet
+ /* No stub for you, sonny Jim */
+alternative_if ARM64_KVM_PROTECTED_MODE
+ b __host_exit
+alternative_else_nop_endif
+
/* Check for a stub HVC call */
cmp x0, #HVC_STUB_HCALL_NR
b.hs __host_exit
@@ -137,6 +134,17 @@ SYM_FUNC_END(__hyp_do_panic)
ldr x5, =__kvm_handle_stub_hvc
hyp_pa x5, x6
br x5
+SYM_FUNC_END(__host_hvc)
+
+.macro host_el1_sync_vect
+ .align 7
+.L__vect_start\@:
+ stp x0, x1, [sp, #-16]!
+ mrs x0, esr_el2
+ lsr x0, x0, #ESR_ELx_EC_SHIFT
+ cmp x0, #ESR_ELx_EC_HVC64
+ b.eq __host_hvc
+ b __host_exit
.L__vect_end\@:
.if ((.L__vect_end\@ - .L__vect_start\@) > 0x80)
.error "host_el1_sync_vect larger than vector entry"
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 2da6aa8da868..b096bf009144 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -4,7 +4,7 @@
* Author: Andrew Scull <ascull@google.com>
*/
-#include <hyp/switch.h>
+#include <hyp/adjust_pc.h>
#include <asm/pgtable-types.h>
#include <asm/kvm_asm.h>
@@ -160,41 +160,65 @@ static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt)
{
cpu_reg(host_ctxt, 1) = __pkvm_prot_finalize();
}
+
+static void handle___pkvm_vcpu_init_traps(struct kvm_cpu_context *host_ctxt)
+{
+ DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1);
+
+ __pkvm_vcpu_init_traps(kern_hyp_va(vcpu));
+}
+
typedef void (*hcall_t)(struct kvm_cpu_context *);
#define HANDLE_FUNC(x) [__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x
static const hcall_t host_hcall[] = {
- HANDLE_FUNC(__kvm_vcpu_run),
+ /* ___kvm_hyp_init */
+ HANDLE_FUNC(__kvm_get_mdcr_el2),
+ HANDLE_FUNC(__pkvm_init),
+ HANDLE_FUNC(__pkvm_create_private_mapping),
+ HANDLE_FUNC(__pkvm_cpu_set_vector),
+ HANDLE_FUNC(__kvm_enable_ssbs),
+ HANDLE_FUNC(__vgic_v3_init_lrs),
+ HANDLE_FUNC(__vgic_v3_get_gic_config),
+ HANDLE_FUNC(__pkvm_prot_finalize),
+
+ HANDLE_FUNC(__pkvm_host_share_hyp),
HANDLE_FUNC(__kvm_adjust_pc),
+ HANDLE_FUNC(__kvm_vcpu_run),
HANDLE_FUNC(__kvm_flush_vm_context),
HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa),
HANDLE_FUNC(__kvm_tlb_flush_vmid),
HANDLE_FUNC(__kvm_flush_cpu_context),
HANDLE_FUNC(__kvm_timer_set_cntvoff),
- HANDLE_FUNC(__kvm_enable_ssbs),
- HANDLE_FUNC(__vgic_v3_get_gic_config),
HANDLE_FUNC(__vgic_v3_read_vmcr),
HANDLE_FUNC(__vgic_v3_write_vmcr),
- HANDLE_FUNC(__vgic_v3_init_lrs),
- HANDLE_FUNC(__kvm_get_mdcr_el2),
HANDLE_FUNC(__vgic_v3_save_aprs),
HANDLE_FUNC(__vgic_v3_restore_aprs),
- HANDLE_FUNC(__pkvm_init),
- HANDLE_FUNC(__pkvm_cpu_set_vector),
- HANDLE_FUNC(__pkvm_host_share_hyp),
- HANDLE_FUNC(__pkvm_create_private_mapping),
- HANDLE_FUNC(__pkvm_prot_finalize),
+ HANDLE_FUNC(__pkvm_vcpu_init_traps),
};
static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
{
DECLARE_REG(unsigned long, id, host_ctxt, 0);
+ unsigned long hcall_min = 0;
hcall_t hfn;
+ /*
+ * If pKVM has been initialised then reject any calls to the
+ * early "privileged" hypercalls. Note that we cannot reject
+ * calls to __pkvm_prot_finalize for two reasons: (1) The static
+ * key used to determine initialisation must be toggled prior to
+ * finalisation and (2) finalisation is performed on a per-CPU
+ * basis. This is all fine, however, since __pkvm_prot_finalize
+ * returns -EPERM after the first call for a given CPU.
+ */
+ if (static_branch_unlikely(&kvm_protected_mode_initialized))
+ hcall_min = __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize;
+
id -= KVM_HOST_SMCCC_ID(0);
- if (unlikely(id >= ARRAY_SIZE(host_hcall)))
+ if (unlikely(id < hcall_min || id >= ARRAY_SIZE(host_hcall)))
goto inval;
hfn = host_hcall[id];
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index bacd493a4eac..1f0fb0780622 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -11,7 +11,7 @@
#include <asm/kvm_pgtable.h>
#include <asm/stage2_pgtable.h>
-#include <hyp/switch.h>
+#include <hyp/fault.h>
#include <nvhe/gfp.h>
#include <nvhe/memory.h>
@@ -25,12 +25,6 @@ struct host_kvm host_kvm;
static struct hyp_pool host_s2_pool;
-/*
- * Copies of the host's CPU features registers holding sanitized values.
- */
-u64 id_aa64mmfr0_el1_sys_val;
-u64 id_aa64mmfr1_el1_sys_val;
-
const u8 pkvm_hyp_id = 1;
static void *host_s2_zalloc_pages_exact(size_t size)
@@ -123,6 +117,9 @@ int __pkvm_prot_finalize(void)
struct kvm_s2_mmu *mmu = &host_kvm.arch.mmu;
struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params);
+ if (params->hcr_el2 & HCR_VM)
+ return -EPERM;
+
params->vttbr = kvm_get_vttbr(mmu);
params->vtcr = host_kvm.arch.vtcr;
params->hcr_el2 |= HCR_VM;
diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c
new file mode 100644
index 000000000000..99c8d8b73e70
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c
@@ -0,0 +1,185 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Google LLC
+ * Author: Fuad Tabba <tabba@google.com>
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/mm.h>
+#include <nvhe/fixed_config.h>
+#include <nvhe/trap_handler.h>
+
+/*
+ * Set trap register values based on features in ID_AA64PFR0.
+ */
+static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu)
+{
+ const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR0_EL1);
+ u64 hcr_set = HCR_RW;
+ u64 hcr_clear = 0;
+ u64 cptr_set = 0;
+
+ /* Protected KVM does not support AArch32 guests. */
+ BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL0),
+ PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_ELx_64BIT_ONLY);
+ BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1),
+ PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_ELx_64BIT_ONLY);
+
+ /*
+ * Linux guests assume support for floating-point and Advanced SIMD. Do
+ * not change the trapping behavior for these from the KVM default.
+ */
+ BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_FP),
+ PVM_ID_AA64PFR0_ALLOW));
+ BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD),
+ PVM_ID_AA64PFR0_ALLOW));
+
+ /* Trap RAS unless all current versions are supported */
+ if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_RAS), feature_ids) <
+ ID_AA64PFR0_RAS_V1P1) {
+ hcr_set |= HCR_TERR | HCR_TEA;
+ hcr_clear |= HCR_FIEN;
+ }
+
+ /* Trap AMU */
+ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_AMU), feature_ids)) {
+ hcr_clear |= HCR_AMVOFFEN;
+ cptr_set |= CPTR_EL2_TAM;
+ }
+
+ /* Trap SVE */
+ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_SVE), feature_ids))
+ cptr_set |= CPTR_EL2_TZ;
+
+ vcpu->arch.hcr_el2 |= hcr_set;
+ vcpu->arch.hcr_el2 &= ~hcr_clear;
+ vcpu->arch.cptr_el2 |= cptr_set;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64PFR1.
+ */
+static void pvm_init_traps_aa64pfr1(struct kvm_vcpu *vcpu)
+{
+ const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR1_EL1);
+ u64 hcr_set = 0;
+ u64 hcr_clear = 0;
+
+ /* Memory Tagging: Trap and Treat as Untagged if not supported. */
+ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_MTE), feature_ids)) {
+ hcr_set |= HCR_TID5;
+ hcr_clear |= HCR_DCT | HCR_ATA;
+ }
+
+ vcpu->arch.hcr_el2 |= hcr_set;
+ vcpu->arch.hcr_el2 &= ~hcr_clear;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64DFR0.
+ */
+static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu)
+{
+ const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64DFR0_EL1);
+ u64 mdcr_set = 0;
+ u64 mdcr_clear = 0;
+ u64 cptr_set = 0;
+
+ /* Trap/constrain PMU */
+ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_PMUVER), feature_ids)) {
+ mdcr_set |= MDCR_EL2_TPM | MDCR_EL2_TPMCR;
+ mdcr_clear |= MDCR_EL2_HPME | MDCR_EL2_MTPME |
+ MDCR_EL2_HPMN_MASK;
+ }
+
+ /* Trap Debug */
+ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_DEBUGVER), feature_ids))
+ mdcr_set |= MDCR_EL2_TDRA | MDCR_EL2_TDA | MDCR_EL2_TDE;
+
+ /* Trap OS Double Lock */
+ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_DOUBLELOCK), feature_ids))
+ mdcr_set |= MDCR_EL2_TDOSA;
+
+ /* Trap SPE */
+ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_PMSVER), feature_ids)) {
+ mdcr_set |= MDCR_EL2_TPMS;
+ mdcr_clear |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT;
+ }
+
+ /* Trap Trace Filter */
+ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_TRACE_FILT), feature_ids))
+ mdcr_set |= MDCR_EL2_TTRF;
+
+ /* Trap Trace */
+ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_TRACEVER), feature_ids))
+ cptr_set |= CPTR_EL2_TTA;
+
+ vcpu->arch.mdcr_el2 |= mdcr_set;
+ vcpu->arch.mdcr_el2 &= ~mdcr_clear;
+ vcpu->arch.cptr_el2 |= cptr_set;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64MMFR0.
+ */
+static void pvm_init_traps_aa64mmfr0(struct kvm_vcpu *vcpu)
+{
+ const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR0_EL1);
+ u64 mdcr_set = 0;
+
+ /* Trap Debug Communications Channel registers */
+ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_FGT), feature_ids))
+ mdcr_set |= MDCR_EL2_TDCC;
+
+ vcpu->arch.mdcr_el2 |= mdcr_set;
+}
+
+/*
+ * Set trap register values based on features in ID_AA64MMFR1.
+ */
+static void pvm_init_traps_aa64mmfr1(struct kvm_vcpu *vcpu)
+{
+ const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR1_EL1);
+ u64 hcr_set = 0;
+
+ /* Trap LOR */
+ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_LOR), feature_ids))
+ hcr_set |= HCR_TLOR;
+
+ vcpu->arch.hcr_el2 |= hcr_set;
+}
+
+/*
+ * Set baseline trap register values.
+ */
+static void pvm_init_trap_regs(struct kvm_vcpu *vcpu)
+{
+ const u64 hcr_trap_feat_regs = HCR_TID3;
+ const u64 hcr_trap_impdef = HCR_TACR | HCR_TIDCP | HCR_TID1;
+
+ /*
+ * Always trap:
+ * - Feature id registers: to control features exposed to guests
+ * - Implementation-defined features
+ */
+ vcpu->arch.hcr_el2 |= hcr_trap_feat_regs | hcr_trap_impdef;
+
+ /* Clear res0 and set res1 bits to trap potential new features. */
+ vcpu->arch.hcr_el2 &= ~(HCR_RES0);
+ vcpu->arch.mdcr_el2 &= ~(MDCR_EL2_RES0);
+ vcpu->arch.cptr_el2 |= CPTR_NVHE_EL2_RES1;
+ vcpu->arch.cptr_el2 &= ~(CPTR_NVHE_EL2_RES0);
+}
+
+/*
+ * Initialize trap register values for protected VMs.
+ */
+void __pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu)
+{
+ pvm_init_trap_regs(vcpu);
+ pvm_init_traps_aa64pfr0(vcpu);
+ pvm_init_traps_aa64pfr1(vcpu);
+ pvm_init_traps_aa64dfr0(vcpu);
+ pvm_init_traps_aa64mmfr0(vcpu);
+ pvm_init_traps_aa64mmfr1(vcpu);
+}
diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
index 57c27846320f..862c7b514e20 100644
--- a/arch/arm64/kvm/hyp/nvhe/setup.c
+++ b/arch/arm64/kvm/hyp/nvhe/setup.c
@@ -10,6 +10,7 @@
#include <asm/kvm_pgtable.h>
#include <nvhe/early_alloc.h>
+#include <nvhe/fixed_config.h>
#include <nvhe/gfp.h>
#include <nvhe/memory.h>
#include <nvhe/mem_protect.h>
@@ -260,6 +261,8 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus,
void (*fn)(phys_addr_t params_pa, void *finalize_fn_va);
int ret;
+ BUG_ON(kvm_check_pvm_sysreg_table());
+
if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size))
return -EINVAL;
diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c
index a34b01cc8ab9..c0e3fed26d93 100644
--- a/arch/arm64/kvm/hyp/nvhe/switch.c
+++ b/arch/arm64/kvm/hyp/nvhe/switch.c
@@ -27,6 +27,7 @@
#include <asm/processor.h>
#include <asm/thread_info.h>
+#include <nvhe/fixed_config.h>
#include <nvhe/mem_protect.h>
/* Non-VHE specific context */
@@ -158,6 +159,101 @@ static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt)
write_sysreg(pmu->events_host, pmcntenset_el0);
}
+/**
+ * Handler for protected VM MSR, MRS or System instruction execution in AArch64.
+ *
+ * Returns true if the hypervisor has handled the exit, and control should go
+ * back to the guest, or false if it hasn't.
+ */
+static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ /*
+ * Make sure we handle the exit for workarounds and ptrauth
+ * before the pKVM handling, as the latter could decide to
+ * UNDEF.
+ */
+ return (kvm_hyp_handle_sysreg(vcpu, exit_code) ||
+ kvm_handle_pvm_sysreg(vcpu, exit_code));
+}
+
+/**
+ * Handler for protected floating-point and Advanced SIMD accesses.
+ *
+ * Returns true if the hypervisor has handled the exit, and control should go
+ * back to the guest, or false if it hasn't.
+ */
+static bool kvm_handle_pvm_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ /* Linux guests assume support for floating-point and Advanced SIMD. */
+ BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_FP),
+ PVM_ID_AA64PFR0_ALLOW));
+ BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD),
+ PVM_ID_AA64PFR0_ALLOW));
+
+ return kvm_hyp_handle_fpsimd(vcpu, exit_code);
+}
+
+static const exit_handler_fn hyp_exit_handlers[] = {
+ [0 ... ESR_ELx_EC_MAX] = NULL,
+ [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32,
+ [ESR_ELx_EC_SYS64] = kvm_hyp_handle_sysreg,
+ [ESR_ELx_EC_SVE] = kvm_hyp_handle_fpsimd,
+ [ESR_ELx_EC_FP_ASIMD] = kvm_hyp_handle_fpsimd,
+ [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low,
+ [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low,
+ [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth,
+};
+
+static const exit_handler_fn pvm_exit_handlers[] = {
+ [0 ... ESR_ELx_EC_MAX] = NULL,
+ [ESR_ELx_EC_SYS64] = kvm_handle_pvm_sys64,
+ [ESR_ELx_EC_SVE] = kvm_handle_pvm_restricted,
+ [ESR_ELx_EC_FP_ASIMD] = kvm_handle_pvm_fpsimd,
+ [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low,
+ [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low,
+ [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth,
+};
+
+static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
+{
+ if (unlikely(kvm_vm_is_protected(kern_hyp_va(vcpu->kvm))))
+ return pvm_exit_handlers;
+
+ return hyp_exit_handlers;
+}
+
+/*
+ * Some guests (e.g., protected VMs) are not be allowed to run in AArch32.
+ * The ARMv8 architecture does not give the hypervisor a mechanism to prevent a
+ * guest from dropping to AArch32 EL0 if implemented by the CPU. If the
+ * hypervisor spots a guest in such a state ensure it is handled, and don't
+ * trust the host to spot or fix it. The check below is based on the one in
+ * kvm_arch_vcpu_ioctl_run().
+ *
+ * Returns false if the guest ran in AArch32 when it shouldn't have, and
+ * thus should exit to the host, or true if a the guest run loop can continue.
+ */
+static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ struct kvm *kvm = kern_hyp_va(vcpu->kvm);
+
+ if (kvm_vm_is_protected(kvm) && vcpu_mode_is_32bit(vcpu)) {
+ /*
+ * As we have caught the guest red-handed, decide that it isn't
+ * fit for purpose anymore by making the vcpu invalid. The VMM
+ * can try and fix it by re-initializing the vcpu with
+ * KVM_ARM_VCPU_INIT, however, this is likely not possible for
+ * protected VMs.
+ */
+ vcpu->arch.target = -1;
+ *exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT);
+ *exit_code |= ARM_EXCEPTION_IL;
+ return false;
+ }
+
+ return true;
+}
+
/* Switch to the guest for legacy non-VHE systems */
int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
{
@@ -220,6 +316,9 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
/* Jump in the fire! */
exit_code = __guest_enter(vcpu);
+ if (unlikely(!handle_aarch32_guest(vcpu, &exit_code)))
+ break;
+
/* And we're baaack! */
} while (fixup_guest_exit(vcpu, &exit_code));
diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
new file mode 100644
index 000000000000..3787ee6fb1a2
--- /dev/null
+++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c
@@ -0,0 +1,487 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Google LLC
+ * Author: Fuad Tabba <tabba@google.com>
+ */
+
+#include <linux/irqchip/arm-gic-v3.h>
+
+#include <asm/kvm_asm.h>
+#include <asm/kvm_mmu.h>
+
+#include <hyp/adjust_pc.h>
+
+#include <nvhe/fixed_config.h>
+
+#include "../../sys_regs.h"
+
+/*
+ * Copies of the host's CPU features registers holding sanitized values at hyp.
+ */
+u64 id_aa64pfr0_el1_sys_val;
+u64 id_aa64pfr1_el1_sys_val;
+u64 id_aa64isar0_el1_sys_val;
+u64 id_aa64isar1_el1_sys_val;
+u64 id_aa64mmfr0_el1_sys_val;
+u64 id_aa64mmfr1_el1_sys_val;
+u64 id_aa64mmfr2_el1_sys_val;
+
+/*
+ * Inject an unknown/undefined exception to an AArch64 guest while most of its
+ * sysregs are live.
+ */
+static void inject_undef64(struct kvm_vcpu *vcpu)
+{
+ u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT);
+
+ *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR);
+ *vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR);
+
+ vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1 |
+ KVM_ARM64_EXCEPT_AA64_ELx_SYNC |
+ KVM_ARM64_PENDING_EXCEPTION);
+
+ __kvm_adjust_pc(vcpu);
+
+ write_sysreg_el1(esr, SYS_ESR);
+ write_sysreg_el1(read_sysreg_el2(SYS_ELR), SYS_ELR);
+ write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR);
+ write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR);
+}
+
+/*
+ * Returns the restricted features values of the feature register based on the
+ * limitations in restrict_fields.
+ * A feature id field value of 0b0000 does not impose any restrictions.
+ * Note: Use only for unsigned feature field values.
+ */
+static u64 get_restricted_features_unsigned(u64 sys_reg_val,
+ u64 restrict_fields)
+{
+ u64 value = 0UL;
+ u64 mask = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0);
+
+ /*
+ * According to the Arm Architecture Reference Manual, feature fields
+ * use increasing values to indicate increases in functionality.
+ * Iterate over the restricted feature fields and calculate the minimum
+ * unsigned value between the one supported by the system, and what the
+ * value is being restricted to.
+ */
+ while (sys_reg_val && restrict_fields) {
+ value |= min(sys_reg_val & mask, restrict_fields & mask);
+ sys_reg_val &= ~mask;
+ restrict_fields &= ~mask;
+ mask <<= ARM64_FEATURE_FIELD_BITS;
+ }
+
+ return value;
+}
+
+/*
+ * Functions that return the value of feature id registers for protected VMs
+ * based on allowed features, system features, and KVM support.
+ */
+
+static u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu)
+{
+ const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm);
+ u64 set_mask = 0;
+ u64 allow_mask = PVM_ID_AA64PFR0_ALLOW;
+
+ if (!vcpu_has_sve(vcpu))
+ allow_mask &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_SVE);
+
+ set_mask |= get_restricted_features_unsigned(id_aa64pfr0_el1_sys_val,
+ PVM_ID_AA64PFR0_RESTRICT_UNSIGNED);
+
+ /* Spectre and Meltdown mitigation in KVM */
+ set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV2),
+ (u64)kvm->arch.pfr0_csv2);
+ set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3),
+ (u64)kvm->arch.pfr0_csv3);
+
+ return (id_aa64pfr0_el1_sys_val & allow_mask) | set_mask;
+}
+
+static u64 get_pvm_id_aa64pfr1(const struct kvm_vcpu *vcpu)
+{
+ const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm);
+ u64 allow_mask = PVM_ID_AA64PFR1_ALLOW;
+
+ if (!kvm_has_mte(kvm))
+ allow_mask &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE);
+
+ return id_aa64pfr1_el1_sys_val & allow_mask;
+}
+
+static u64 get_pvm_id_aa64zfr0(const struct kvm_vcpu *vcpu)
+{
+ /*
+ * No support for Scalable Vectors, therefore, hyp has no sanitized
+ * copy of the feature id register.
+ */
+ BUILD_BUG_ON(PVM_ID_AA64ZFR0_ALLOW != 0ULL);
+ return 0;
+}
+
+static u64 get_pvm_id_aa64dfr0(const struct kvm_vcpu *vcpu)
+{
+ /*
+ * No support for debug, including breakpoints, and watchpoints,
+ * therefore, pKVM has no sanitized copy of the feature id register.
+ */
+ BUILD_BUG_ON(PVM_ID_AA64DFR0_ALLOW != 0ULL);
+ return 0;
+}
+
+static u64 get_pvm_id_aa64dfr1(const struct kvm_vcpu *vcpu)
+{
+ /*
+ * No support for debug, therefore, hyp has no sanitized copy of the
+ * feature id register.
+ */
+ BUILD_BUG_ON(PVM_ID_AA64DFR1_ALLOW != 0ULL);
+ return 0;
+}
+
+static u64 get_pvm_id_aa64afr0(const struct kvm_vcpu *vcpu)
+{
+ /*
+ * No support for implementation defined features, therefore, hyp has no
+ * sanitized copy of the feature id register.
+ */
+ BUILD_BUG_ON(PVM_ID_AA64AFR0_ALLOW != 0ULL);
+ return 0;
+}
+
+static u64 get_pvm_id_aa64afr1(const struct kvm_vcpu *vcpu)
+{
+ /*
+ * No support for implementation defined features, therefore, hyp has no
+ * sanitized copy of the feature id register.
+ */
+ BUILD_BUG_ON(PVM_ID_AA64AFR1_ALLOW != 0ULL);
+ return 0;
+}
+
+static u64 get_pvm_id_aa64isar0(const struct kvm_vcpu *vcpu)
+{
+ return id_aa64isar0_el1_sys_val & PVM_ID_AA64ISAR0_ALLOW;
+}
+
+static u64 get_pvm_id_aa64isar1(const struct kvm_vcpu *vcpu)
+{
+ u64 allow_mask = PVM_ID_AA64ISAR1_ALLOW;
+
+ if (!vcpu_has_ptrauth(vcpu))
+ allow_mask &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR1_APA) |
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_API) |
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_GPA) |
+ ARM64_FEATURE_MASK(ID_AA64ISAR1_GPI));
+
+ return id_aa64isar1_el1_sys_val & allow_mask;
+}
+
+static u64 get_pvm_id_aa64mmfr0(const struct kvm_vcpu *vcpu)
+{
+ u64 set_mask;
+
+ set_mask = get_restricted_features_unsigned(id_aa64mmfr0_el1_sys_val,
+ PVM_ID_AA64MMFR0_RESTRICT_UNSIGNED);
+
+ return (id_aa64mmfr0_el1_sys_val & PVM_ID_AA64MMFR0_ALLOW) | set_mask;
+}
+
+static u64 get_pvm_id_aa64mmfr1(const struct kvm_vcpu *vcpu)
+{
+ return id_aa64mmfr1_el1_sys_val & PVM_ID_AA64MMFR1_ALLOW;
+}
+
+static u64 get_pvm_id_aa64mmfr2(const struct kvm_vcpu *vcpu)
+{
+ return id_aa64mmfr2_el1_sys_val & PVM_ID_AA64MMFR2_ALLOW;
+}
+
+/* Read a sanitized cpufeature ID register by its encoding */
+u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id)
+{
+ switch (id) {
+ case SYS_ID_AA64PFR0_EL1:
+ return get_pvm_id_aa64pfr0(vcpu);
+ case SYS_ID_AA64PFR1_EL1:
+ return get_pvm_id_aa64pfr1(vcpu);
+ case SYS_ID_AA64ZFR0_EL1:
+ return get_pvm_id_aa64zfr0(vcpu);
+ case SYS_ID_AA64DFR0_EL1:
+ return get_pvm_id_aa64dfr0(vcpu);
+ case SYS_ID_AA64DFR1_EL1:
+ return get_pvm_id_aa64dfr1(vcpu);
+ case SYS_ID_AA64AFR0_EL1:
+ return get_pvm_id_aa64afr0(vcpu);
+ case SYS_ID_AA64AFR1_EL1:
+ return get_pvm_id_aa64afr1(vcpu);
+ case SYS_ID_AA64ISAR0_EL1:
+ return get_pvm_id_aa64isar0(vcpu);
+ case SYS_ID_AA64ISAR1_EL1:
+ return get_pvm_id_aa64isar1(vcpu);
+ case SYS_ID_AA64MMFR0_EL1:
+ return get_pvm_id_aa64mmfr0(vcpu);
+ case SYS_ID_AA64MMFR1_EL1:
+ return get_pvm_id_aa64mmfr1(vcpu);
+ case SYS_ID_AA64MMFR2_EL1:
+ return get_pvm_id_aa64mmfr2(vcpu);
+ default:
+ /*
+ * Should never happen because all cases are covered in
+ * pvm_sys_reg_descs[].
+ */
+ WARN_ON(1);
+ break;
+ }
+
+ return 0;
+}
+
+static u64 read_id_reg(const struct kvm_vcpu *vcpu,
+ struct sys_reg_desc const *r)
+{
+ return pvm_read_id_reg(vcpu, reg_to_encoding(r));
+}
+
+/* Handler to RAZ/WI sysregs */
+static bool pvm_access_raz_wi(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (!p->is_write)
+ p->regval = 0;
+
+ return true;
+}
+
+/*
+ * Accessor for AArch32 feature id registers.
+ *
+ * The value of these registers is "unknown" according to the spec if AArch32
+ * isn't supported.
+ */
+static bool pvm_access_id_aarch32(struct kvm_vcpu *vcpu,
+ struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ inject_undef64(vcpu);
+ return false;
+ }
+
+ /*
+ * No support for AArch32 guests, therefore, pKVM has no sanitized copy
+ * of AArch32 feature id registers.
+ */
+ BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1),
+ PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) > ID_AA64PFR0_ELx_64BIT_ONLY);
+
+ return pvm_access_raz_wi(vcpu, p, r);
+}
+
+/*
+ * Accessor for AArch64 feature id registers.
+ *
+ * If access is allowed, set the regval to the protected VM's view of the
+ * register and return true.
+ * Otherwise, inject an undefined exception and return false.
+ */
+static bool pvm_access_id_aarch64(struct kvm_vcpu *vcpu,
+ struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ if (p->is_write) {
+ inject_undef64(vcpu);
+ return false;
+ }
+
+ p->regval = read_id_reg(vcpu, r);
+ return true;
+}
+
+static bool pvm_gic_read_sre(struct kvm_vcpu *vcpu,
+ struct sys_reg_params *p,
+ const struct sys_reg_desc *r)
+{
+ /* pVMs only support GICv3. 'nuf said. */
+ if (!p->is_write)
+ p->regval = ICC_SRE_EL1_DIB | ICC_SRE_EL1_DFB | ICC_SRE_EL1_SRE;
+
+ return true;
+}
+
+/* Mark the specified system register as an AArch32 feature id register. */
+#define AARCH32(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch32 }
+
+/* Mark the specified system register as an AArch64 feature id register. */
+#define AARCH64(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch64 }
+
+/* Mark the specified system register as Read-As-Zero/Write-Ignored */
+#define RAZ_WI(REG) { SYS_DESC(REG), .access = pvm_access_raz_wi }
+
+/* Mark the specified system register as not being handled in hyp. */
+#define HOST_HANDLED(REG) { SYS_DESC(REG), .access = NULL }
+
+/*
+ * Architected system registers.
+ * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2
+ *
+ * NOTE: Anything not explicitly listed here is *restricted by default*, i.e.,
+ * it will lead to injecting an exception into the guest.
+ */
+static const struct sys_reg_desc pvm_sys_reg_descs[] = {
+ /* Cache maintenance by set/way operations are restricted. */
+
+ /* Debug and Trace Registers are restricted. */
+
+ /* AArch64 mappings of the AArch32 ID registers */
+ /* CRm=1 */
+ AARCH32(SYS_ID_PFR0_EL1),
+ AARCH32(SYS_ID_PFR1_EL1),
+ AARCH32(SYS_ID_DFR0_EL1),
+ AARCH32(SYS_ID_AFR0_EL1),
+ AARCH32(SYS_ID_MMFR0_EL1),
+ AARCH32(SYS_ID_MMFR1_EL1),
+ AARCH32(SYS_ID_MMFR2_EL1),
+ AARCH32(SYS_ID_MMFR3_EL1),
+
+ /* CRm=2 */
+ AARCH32(SYS_ID_ISAR0_EL1),
+ AARCH32(SYS_ID_ISAR1_EL1),
+ AARCH32(SYS_ID_ISAR2_EL1),
+ AARCH32(SYS_ID_ISAR3_EL1),
+ AARCH32(SYS_ID_ISAR4_EL1),
+ AARCH32(SYS_ID_ISAR5_EL1),
+ AARCH32(SYS_ID_MMFR4_EL1),
+ AARCH32(SYS_ID_ISAR6_EL1),
+
+ /* CRm=3 */
+ AARCH32(SYS_MVFR0_EL1),
+ AARCH32(SYS_MVFR1_EL1),
+ AARCH32(SYS_MVFR2_EL1),
+ AARCH32(SYS_ID_PFR2_EL1),
+ AARCH32(SYS_ID_DFR1_EL1),
+ AARCH32(SYS_ID_MMFR5_EL1),
+
+ /* AArch64 ID registers */
+ /* CRm=4 */
+ AARCH64(SYS_ID_AA64PFR0_EL1),
+ AARCH64(SYS_ID_AA64PFR1_EL1),
+ AARCH64(SYS_ID_AA64ZFR0_EL1),
+ AARCH64(SYS_ID_AA64DFR0_EL1),
+ AARCH64(SYS_ID_AA64DFR1_EL1),
+ AARCH64(SYS_ID_AA64AFR0_EL1),
+ AARCH64(SYS_ID_AA64AFR1_EL1),
+ AARCH64(SYS_ID_AA64ISAR0_EL1),
+ AARCH64(SYS_ID_AA64ISAR1_EL1),
+ AARCH64(SYS_ID_AA64MMFR0_EL1),
+ AARCH64(SYS_ID_AA64MMFR1_EL1),
+ AARCH64(SYS_ID_AA64MMFR2_EL1),
+
+ /* Scalable Vector Registers are restricted. */
+
+ RAZ_WI(SYS_ERRIDR_EL1),
+ RAZ_WI(SYS_ERRSELR_EL1),
+ RAZ_WI(SYS_ERXFR_EL1),
+ RAZ_WI(SYS_ERXCTLR_EL1),
+ RAZ_WI(SYS_ERXSTATUS_EL1),
+ RAZ_WI(SYS_ERXADDR_EL1),
+ RAZ_WI(SYS_ERXMISC0_EL1),
+ RAZ_WI(SYS_ERXMISC1_EL1),
+
+ /* Performance Monitoring Registers are restricted. */
+
+ /* Limited Ordering Regions Registers are restricted. */
+
+ HOST_HANDLED(SYS_ICC_SGI1R_EL1),
+ HOST_HANDLED(SYS_ICC_ASGI1R_EL1),
+ HOST_HANDLED(SYS_ICC_SGI0R_EL1),
+ { SYS_DESC(SYS_ICC_SRE_EL1), .access = pvm_gic_read_sre, },
+
+ HOST_HANDLED(SYS_CCSIDR_EL1),
+ HOST_HANDLED(SYS_CLIDR_EL1),
+ HOST_HANDLED(SYS_CSSELR_EL1),
+ HOST_HANDLED(SYS_CTR_EL0),
+
+ /* Performance Monitoring Registers are restricted. */
+
+ /* Activity Monitoring Registers are restricted. */
+
+ HOST_HANDLED(SYS_CNTP_TVAL_EL0),
+ HOST_HANDLED(SYS_CNTP_CTL_EL0),
+ HOST_HANDLED(SYS_CNTP_CVAL_EL0),
+
+ /* Performance Monitoring Registers are restricted. */
+};
+
+/*
+ * Checks that the sysreg table is unique and in-order.
+ *
+ * Returns 0 if the table is consistent, or 1 otherwise.
+ */
+int kvm_check_pvm_sysreg_table(void)
+{
+ unsigned int i;
+
+ for (i = 1; i < ARRAY_SIZE(pvm_sys_reg_descs); i++) {
+ if (cmp_sys_reg(&pvm_sys_reg_descs[i-1], &pvm_sys_reg_descs[i]) >= 0)
+ return 1;
+ }
+
+ return 0;
+}
+
+/*
+ * Handler for protected VM MSR, MRS or System instruction execution.
+ *
+ * Returns true if the hypervisor has handled the exit, and control should go
+ * back to the guest, or false if it hasn't, to be handled by the host.
+ */
+bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ const struct sys_reg_desc *r;
+ struct sys_reg_params params;
+ unsigned long esr = kvm_vcpu_get_esr(vcpu);
+ int Rt = kvm_vcpu_sys_get_rt(vcpu);
+
+ params = esr_sys64_to_params(esr);
+ params.regval = vcpu_get_reg(vcpu, Rt);
+
+ r = find_reg(&params, pvm_sys_reg_descs, ARRAY_SIZE(pvm_sys_reg_descs));
+
+ /* Undefined (RESTRICTED). */
+ if (r == NULL) {
+ inject_undef64(vcpu);
+ return true;
+ }
+
+ /* Handled by the host (HOST_HANDLED) */
+ if (r->access == NULL)
+ return false;
+
+ /* Handled by hyp: skip instruction if instructed to do so. */
+ if (r->access(vcpu, &params, r))
+ __kvm_skip_instr(vcpu);
+
+ if (!params.is_write)
+ vcpu_set_reg(vcpu, Rt, params.regval);
+
+ return true;
+}
+
+/**
+ * Handler for protected VM restricted exceptions.
+ *
+ * Inject an undefined exception into the guest and return true to indicate that
+ * the hypervisor has handled the exit, and control should go back to the guest.
+ */
+bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+ inject_undef64(vcpu);
+ return true;
+}
diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c
index 39f8f7f9227c..20db2f281cf2 100644
--- a/arch/arm64/kvm/hyp/vgic-v3-sr.c
+++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c
@@ -695,9 +695,7 @@ static void __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
goto spurious;
lr_val &= ~ICH_LR_STATE;
- /* No active state for LPIs */
- if ((lr_val & ICH_LR_VIRTUAL_ID_MASK) <= VGIC_MAX_SPI)
- lr_val |= ICH_LR_ACTIVE_BIT;
+ lr_val |= ICH_LR_ACTIVE_BIT;
__gic_v3_set_lr(lr_val, lr);
__vgic_v3_set_active_priority(lr_prio, vmcr, grp);
vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK);
@@ -764,20 +762,18 @@ static void __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
/* Drop priority in any case */
act_prio = __vgic_v3_clear_highest_active_priority();
- /* If EOIing an LPI, no deactivate to be performed */
- if (vid >= VGIC_MIN_LPI)
- return;
-
- /* EOImode == 1, nothing to be done here */
- if (vmcr & ICH_VMCR_EOIM_MASK)
- return;
-
lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val);
if (lr == -1) {
- __vgic_v3_bump_eoicount();
+ /* Do not bump EOIcount for LPIs that aren't in the LRs */
+ if (!(vid >= VGIC_MIN_LPI))
+ __vgic_v3_bump_eoicount();
return;
}
+ /* EOImode == 1 and not an LPI, nothing to be done here */
+ if ((vmcr & ICH_VMCR_EOIM_MASK) && !(vid >= VGIC_MIN_LPI))
+ return;
+
lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT;
/* If priorities or group do not match, the guest has fscked-up. */
@@ -987,8 +983,6 @@ static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt)
val = ((vtr >> 29) & 7) << ICC_CTLR_EL1_PRI_BITS_SHIFT;
/* IDbits */
val |= ((vtr >> 23) & 7) << ICC_CTLR_EL1_ID_BITS_SHIFT;
- /* SEIS */
- val |= ((vtr >> 22) & 1) << ICC_CTLR_EL1_SEIS_SHIFT;
/* A3V */
val |= ((vtr >> 21) & 1) << ICC_CTLR_EL1_A3V_SHIFT;
/* EOImode */
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index ded2c66675f0..5a2cb5d9bc4b 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -96,6 +96,22 @@ void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu)
__deactivate_traps_common(vcpu);
}
+static const exit_handler_fn hyp_exit_handlers[] = {
+ [0 ... ESR_ELx_EC_MAX] = NULL,
+ [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32,
+ [ESR_ELx_EC_SYS64] = kvm_hyp_handle_sysreg,
+ [ESR_ELx_EC_SVE] = kvm_hyp_handle_fpsimd,
+ [ESR_ELx_EC_FP_ASIMD] = kvm_hyp_handle_fpsimd,
+ [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low,
+ [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low,
+ [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth,
+};
+
+static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
+{
+ return hyp_exit_handlers;
+}
+
/* Switch to the guest for VHE systems running in EL2 */
static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
{
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 1a94a7ca48f2..da10996dcdf1 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -512,7 +512,7 @@ int kvm_init_stage2_mmu(struct kvm *kvm, struct kvm_s2_mmu *mmu)
return -EINVAL;
}
- pgt = kzalloc(sizeof(*pgt), GFP_KERNEL);
+ pgt = kzalloc(sizeof(*pgt), GFP_KERNEL_ACCOUNT);
if (!pgt)
return -ENOMEM;
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 2af3c37445e0..a5e4bbf5e68f 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -978,7 +978,7 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
mutex_lock(&vcpu->kvm->lock);
if (!vcpu->kvm->arch.pmu_filter) {
- vcpu->kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL);
+ vcpu->kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL_ACCOUNT);
if (!vcpu->kvm->arch.pmu_filter) {
mutex_unlock(&vcpu->kvm->lock);
return -ENOMEM;
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index 5ce36b0a3343..acad22ebac12 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -106,7 +106,7 @@ static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu)
vl > SVE_VL_ARCH_MAX))
return -EIO;
- buf = kzalloc(SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)), GFP_KERNEL);
+ buf = kzalloc(SVE_SIG_REGS_SIZE(sve_vq_from_vl(vl)), GFP_KERNEL_ACCOUNT);
if (!buf)
return -ENOMEM;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 1d46e185f31e..e3ec1a44f94d 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1064,7 +1064,12 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
struct sys_reg_desc const *r, bool raz)
{
u32 id = reg_to_encoding(r);
- u64 val = raz ? 0 : read_sanitised_ftr_reg(id);
+ u64 val;
+
+ if (raz)
+ return 0;
+
+ val = read_sanitised_ftr_reg(id);
switch (id) {
case SYS_ID_AA64PFR0_EL1:
@@ -1075,16 +1080,15 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV2), (u64)vcpu->kvm->arch.pfr0_csv2);
val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3);
val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3), (u64)vcpu->kvm->arch.pfr0_csv3);
+ if (irqchip_in_kernel(vcpu->kvm) &&
+ vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) {
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_GIC);
+ val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_GIC), 1);
+ }
break;
case SYS_ID_AA64PFR1_EL1:
- val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE);
- if (kvm_has_mte(vcpu->kvm)) {
- u64 pfr, mte;
-
- pfr = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1);
- mte = cpuid_feature_extract_unsigned_field(pfr, ID_AA64PFR1_MTE_SHIFT);
- val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR1_MTE), mte);
- }
+ if (!kvm_has_mte(vcpu->kvm))
+ val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE);
break;
case SYS_ID_AA64ISAR1_EL1:
if (!vcpu_has_ptrauth(vcpu))
@@ -1268,16 +1272,19 @@ static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
return __set_id_reg(vcpu, rd, uaddr, raz);
}
-static int get_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+static int set_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
const struct kvm_one_reg *reg, void __user *uaddr)
{
- return __get_id_reg(vcpu, rd, uaddr, true);
+ return __set_id_reg(vcpu, rd, uaddr, true);
}
-static int set_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
- const struct kvm_one_reg *reg, void __user *uaddr)
+static int get_raz_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
+ const struct kvm_one_reg *reg, void __user *uaddr)
{
- return __set_id_reg(vcpu, rd, uaddr, true);
+ const u64 id = sys_reg_to_index(rd);
+ const u64 val = 0;
+
+ return reg_to_user(uaddr, &val, id);
}
static int set_wi_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
@@ -1388,7 +1395,7 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
#define ID_UNALLOCATED(crm, op2) { \
Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2), \
.access = access_raz_id_reg, \
- .get_user = get_raz_id_reg, \
+ .get_user = get_raz_reg, \
.set_user = set_raz_id_reg, \
}
@@ -1400,7 +1407,7 @@ static unsigned int mte_visibility(const struct kvm_vcpu *vcpu,
#define ID_HIDDEN(name) { \
SYS_DESC(SYS_##name), \
.access = access_raz_id_reg, \
- .get_user = get_raz_id_reg, \
+ .get_user = get_raz_reg, \
.set_user = set_raz_id_reg, \
}
@@ -1642,7 +1649,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
* previously (and pointlessly) advertised in the past...
*/
{ PMU_SYS_REG(SYS_PMSWINC_EL0),
- .get_user = get_raz_id_reg, .set_user = set_wi_reg,
+ .get_user = get_raz_reg, .set_user = set_wi_reg,
.access = access_pmswinc, .reset = NULL },
{ PMU_SYS_REG(SYS_PMSELR_EL0),
.access = access_pmselr, .reset = reset_pmselr, .reg = PMSELR_EL0 },
diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c
index 340c51d87677..0a06d0648970 100644
--- a/arch/arm64/kvm/vgic/vgic-init.c
+++ b/arch/arm64/kvm/vgic/vgic-init.c
@@ -134,7 +134,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
struct kvm_vcpu *vcpu0 = kvm_get_vcpu(kvm, 0);
int i;
- dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL);
+ dist->spis = kcalloc(nr_spis, sizeof(struct vgic_irq), GFP_KERNEL_ACCOUNT);
if (!dist->spis)
return -ENOMEM;
diff --git a/arch/arm64/kvm/vgic/vgic-irqfd.c b/arch/arm64/kvm/vgic/vgic-irqfd.c
index 79f8899b234c..475059bacedf 100644
--- a/arch/arm64/kvm/vgic/vgic-irqfd.c
+++ b/arch/arm64/kvm/vgic/vgic-irqfd.c
@@ -139,7 +139,7 @@ int kvm_vgic_setup_default_irq_routing(struct kvm *kvm)
u32 nr = dist->nr_spis;
int i, ret;
- entries = kcalloc(nr, sizeof(*entries), GFP_KERNEL);
+ entries = kcalloc(nr, sizeof(*entries), GFP_KERNEL_ACCOUNT);
if (!entries)
return -ENOMEM;
diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 61728c543eb9..089fc2ffcb43 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -48,7 +48,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
if (irq)
return irq;
- irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL);
+ irq = kzalloc(sizeof(struct vgic_irq), GFP_KERNEL_ACCOUNT);
if (!irq)
return ERR_PTR(-ENOMEM);
@@ -332,7 +332,7 @@ int vgic_copy_lpi_list(struct kvm *kvm, struct kvm_vcpu *vcpu, u32 **intid_ptr)
* we must be careful not to overrun the array.
*/
irq_count = READ_ONCE(dist->lpi_list_count);
- intids = kmalloc_array(irq_count, sizeof(intids[0]), GFP_KERNEL);
+ intids = kmalloc_array(irq_count, sizeof(intids[0]), GFP_KERNEL_ACCOUNT);
if (!intids)
return -ENOMEM;
@@ -985,7 +985,7 @@ static int vgic_its_alloc_collection(struct vgic_its *its,
if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL))
return E_ITS_MAPC_COLLECTION_OOR;
- collection = kzalloc(sizeof(*collection), GFP_KERNEL);
+ collection = kzalloc(sizeof(*collection), GFP_KERNEL_ACCOUNT);
if (!collection)
return -ENOMEM;
@@ -1029,7 +1029,7 @@ static struct its_ite *vgic_its_alloc_ite(struct its_device *device,
{
struct its_ite *ite;
- ite = kzalloc(sizeof(*ite), GFP_KERNEL);
+ ite = kzalloc(sizeof(*ite), GFP_KERNEL_ACCOUNT);
if (!ite)
return ERR_PTR(-ENOMEM);
@@ -1150,7 +1150,7 @@ static struct its_device *vgic_its_alloc_device(struct vgic_its *its,
{
struct its_device *device;
- device = kzalloc(sizeof(*device), GFP_KERNEL);
+ device = kzalloc(sizeof(*device), GFP_KERNEL_ACCOUNT);
if (!device)
return ERR_PTR(-ENOMEM);
@@ -1847,7 +1847,7 @@ void vgic_lpi_translation_cache_init(struct kvm *kvm)
struct vgic_translation_cache_entry *cte;
/* An allocation failure is not fatal */
- cte = kzalloc(sizeof(*cte), GFP_KERNEL);
+ cte = kzalloc(sizeof(*cte), GFP_KERNEL_ACCOUNT);
if (WARN_ON(!cte))
break;
@@ -1888,7 +1888,7 @@ static int vgic_its_create(struct kvm_device *dev, u32 type)
if (type != KVM_DEV_TYPE_ARM_VGIC_ITS)
return -ENODEV;
- its = kzalloc(sizeof(struct vgic_its), GFP_KERNEL);
+ its = kzalloc(sizeof(struct vgic_its), GFP_KERNEL_ACCOUNT);
if (!its)
return -ENOMEM;
@@ -2710,8 +2710,8 @@ static int vgic_its_set_attr(struct kvm_device *dev,
if (copy_from_user(&addr, uaddr, sizeof(addr)))
return -EFAULT;
- ret = vgic_check_ioaddr(dev->kvm, &its->vgic_its_base,
- addr, SZ_64K);
+ ret = vgic_check_iorange(dev->kvm, its->vgic_its_base,
+ addr, SZ_64K, KVM_VGIC_V3_ITS_SIZE);
if (ret)
return ret;
diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c
index 7740995de982..0d000d2fe8d2 100644
--- a/arch/arm64/kvm/vgic/vgic-kvm-device.c
+++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c
@@ -14,17 +14,21 @@
/* common helpers */
-int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
- phys_addr_t addr, phys_addr_t alignment)
+int vgic_check_iorange(struct kvm *kvm, phys_addr_t ioaddr,
+ phys_addr_t addr, phys_addr_t alignment,
+ phys_addr_t size)
{
- if (addr & ~kvm_phys_mask(kvm))
- return -E2BIG;
+ if (!IS_VGIC_ADDR_UNDEF(ioaddr))
+ return -EEXIST;
- if (!IS_ALIGNED(addr, alignment))
+ if (!IS_ALIGNED(addr, alignment) || !IS_ALIGNED(size, alignment))
return -EINVAL;
- if (!IS_VGIC_ADDR_UNDEF(*ioaddr))
- return -EEXIST;
+ if (addr + size < addr)
+ return -EINVAL;
+
+ if (addr & ~kvm_phys_mask(kvm) || addr + size > kvm_phys_size(kvm))
+ return -E2BIG;
return 0;
}
@@ -57,7 +61,7 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
{
int r = 0;
struct vgic_dist *vgic = &kvm->arch.vgic;
- phys_addr_t *addr_ptr, alignment;
+ phys_addr_t *addr_ptr, alignment, size;
u64 undef_value = VGIC_ADDR_UNDEF;
mutex_lock(&kvm->lock);
@@ -66,16 +70,19 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
addr_ptr = &vgic->vgic_dist_base;
alignment = SZ_4K;
+ size = KVM_VGIC_V2_DIST_SIZE;
break;
case KVM_VGIC_V2_ADDR_TYPE_CPU:
r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
addr_ptr = &vgic->vgic_cpu_base;
alignment = SZ_4K;
+ size = KVM_VGIC_V2_CPU_SIZE;
break;
case KVM_VGIC_V3_ADDR_TYPE_DIST:
r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
addr_ptr = &vgic->vgic_dist_base;
alignment = SZ_64K;
+ size = KVM_VGIC_V3_DIST_SIZE;
break;
case KVM_VGIC_V3_ADDR_TYPE_REDIST: {
struct vgic_redist_region *rdreg;
@@ -140,7 +147,7 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
goto out;
if (write) {
- r = vgic_check_ioaddr(kvm, addr_ptr, *addr, alignment);
+ r = vgic_check_iorange(kvm, *addr_ptr, *addr, alignment, size);
if (!r)
*addr_ptr = *addr;
} else {
diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
index a09cdc0b953c..bf7ec4a78497 100644
--- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c
@@ -796,7 +796,9 @@ static int vgic_v3_alloc_redist_region(struct kvm *kvm, uint32_t index,
struct vgic_dist *d = &kvm->arch.vgic;
struct vgic_redist_region *rdreg;
struct list_head *rd_regions = &d->rd_regions;
- size_t size = count * KVM_VGIC_V3_REDIST_SIZE;
+ int nr_vcpus = atomic_read(&kvm->online_vcpus);
+ size_t size = count ? count * KVM_VGIC_V3_REDIST_SIZE
+ : nr_vcpus * KVM_VGIC_V3_REDIST_SIZE;
int ret;
/* cross the end of memory ? */
@@ -834,13 +836,13 @@ static int vgic_v3_alloc_redist_region(struct kvm *kvm, uint32_t index,
if (vgic_v3_rdist_overlap(kvm, base, size))
return -EINVAL;
- rdreg = kzalloc(sizeof(*rdreg), GFP_KERNEL);
+ rdreg = kzalloc(sizeof(*rdreg), GFP_KERNEL_ACCOUNT);
if (!rdreg)
return -ENOMEM;
rdreg->base = VGIC_ADDR_UNDEF;
- ret = vgic_check_ioaddr(kvm, &rdreg->base, base, SZ_64K);
+ ret = vgic_check_iorange(kvm, rdreg->base, base, SZ_64K, size);
if (ret)
goto free;
diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c
index 21a6207fb2ee..04f62c4b07fb 100644
--- a/arch/arm64/kvm/vgic/vgic-v3.c
+++ b/arch/arm64/kvm/vgic/vgic-v3.c
@@ -15,6 +15,7 @@
static bool group0_trap;
static bool group1_trap;
static bool common_trap;
+static bool dir_trap;
static bool gicv4_enable;
void vgic_v3_set_underflow(struct kvm_vcpu *vcpu)
@@ -296,6 +297,8 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
vgic_v3->vgic_hcr |= ICH_HCR_TALL1;
if (common_trap)
vgic_v3->vgic_hcr |= ICH_HCR_TC;
+ if (dir_trap)
+ vgic_v3->vgic_hcr |= ICH_HCR_TDIR;
}
int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
@@ -483,8 +486,10 @@ bool vgic_v3_check_base(struct kvm *kvm)
return false;
list_for_each_entry(rdreg, &d->rd_regions, list) {
- if (rdreg->base + vgic_v3_rd_region_size(kvm, rdreg) <
- rdreg->base)
+ size_t sz = vgic_v3_rd_region_size(kvm, rdreg);
+
+ if (vgic_check_iorange(kvm, VGIC_ADDR_UNDEF,
+ rdreg->base, SZ_64K, sz))
return false;
}
@@ -671,11 +676,23 @@ int vgic_v3_probe(const struct gic_kvm_info *info)
group1_trap = true;
}
- if (group0_trap || group1_trap || common_trap) {
- kvm_info("GICv3 sysreg trapping enabled ([%s%s%s], reduced performance)\n",
+ if (kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) {
+ kvm_info("GICv3 with locally generated SEI\n");
+
+ group0_trap = true;
+ group1_trap = true;
+ if (ich_vtr_el2 & ICH_VTR_TDS_MASK)
+ dir_trap = true;
+ else
+ common_trap = true;
+ }
+
+ if (group0_trap || group1_trap || common_trap | dir_trap) {
+ kvm_info("GICv3 sysreg trapping enabled ([%s%s%s%s], reduced performance)\n",
group0_trap ? "G0" : "",
group1_trap ? "G1" : "",
- common_trap ? "C" : "");
+ common_trap ? "C" : "",
+ dir_trap ? "D" : "");
static_branch_enable(&vgic_v3_cpuif_trap);
}
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index c1845d8f5f7e..772dd15a22c7 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -246,7 +246,7 @@ int vgic_v4_init(struct kvm *kvm)
nr_vcpus = atomic_read(&kvm->online_vcpus);
dist->its_vm.vpes = kcalloc(nr_vcpus, sizeof(*dist->its_vm.vpes),
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
if (!dist->its_vm.vpes)
return -ENOMEM;
diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
index 14a9218641f5..3fd6c86a7ef3 100644
--- a/arch/arm64/kvm/vgic/vgic.h
+++ b/arch/arm64/kvm/vgic/vgic.h
@@ -172,8 +172,9 @@ void vgic_kick_vcpus(struct kvm *kvm);
void vgic_irq_handle_resampling(struct vgic_irq *irq,
bool lr_deactivated, bool lr_pending);
-int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
- phys_addr_t addr, phys_addr_t alignment);
+int vgic_check_iorange(struct kvm *kvm, phys_addr_t ioaddr,
+ phys_addr_t addr, phys_addr_t alignment,
+ phys_addr_t size);
void vgic_v2_fold_lr_state(struct kvm_vcpu *vcpu);
void vgic_v2_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr);
diff --git a/tools/arch/arm64/include/asm/sysreg.h b/tools/arch/arm64/include/asm/sysreg.h
new file mode 100644
index 000000000000..7640fa27be94
--- /dev/null
+++ b/tools/arch/arm64/include/asm/sysreg.h
@@ -0,0 +1,1296 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Macros for accessing system registers with older binutils.
+ *
+ * Copyright (C) 2014 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ */
+
+#ifndef __ASM_SYSREG_H
+#define __ASM_SYSREG_H
+
+#include <linux/bits.h>
+#include <linux/stringify.h>
+
+/*
+ * ARMv8 ARM reserves the following encoding for system registers:
+ * (Ref: ARMv8 ARM, Section: "System instruction class encoding overview",
+ * C5.2, version:ARM DDI 0487A.f)
+ * [20-19] : Op0
+ * [18-16] : Op1
+ * [15-12] : CRn
+ * [11-8] : CRm
+ * [7-5] : Op2
+ */
+#define Op0_shift 19
+#define Op0_mask 0x3
+#define Op1_shift 16
+#define Op1_mask 0x7
+#define CRn_shift 12
+#define CRn_mask 0xf
+#define CRm_shift 8
+#define CRm_mask 0xf
+#define Op2_shift 5
+#define Op2_mask 0x7
+
+#define sys_reg(op0, op1, crn, crm, op2) \
+ (((op0) << Op0_shift) | ((op1) << Op1_shift) | \
+ ((crn) << CRn_shift) | ((crm) << CRm_shift) | \
+ ((op2) << Op2_shift))
+
+#define sys_insn sys_reg
+
+#define sys_reg_Op0(id) (((id) >> Op0_shift) & Op0_mask)
+#define sys_reg_Op1(id) (((id) >> Op1_shift) & Op1_mask)
+#define sys_reg_CRn(id) (((id) >> CRn_shift) & CRn_mask)
+#define sys_reg_CRm(id) (((id) >> CRm_shift) & CRm_mask)
+#define sys_reg_Op2(id) (((id) >> Op2_shift) & Op2_mask)
+
+#ifndef CONFIG_BROKEN_GAS_INST
+
+#ifdef __ASSEMBLY__
+// The space separator is omitted so that __emit_inst(x) can be parsed as
+// either an assembler directive or an assembler macro argument.
+#define __emit_inst(x) .inst(x)
+#else
+#define __emit_inst(x) ".inst " __stringify((x)) "\n\t"
+#endif
+
+#else /* CONFIG_BROKEN_GAS_INST */
+
+#ifndef CONFIG_CPU_BIG_ENDIAN
+#define __INSTR_BSWAP(x) (x)
+#else /* CONFIG_CPU_BIG_ENDIAN */
+#define __INSTR_BSWAP(x) ((((x) << 24) & 0xff000000) | \
+ (((x) << 8) & 0x00ff0000) | \
+ (((x) >> 8) & 0x0000ff00) | \
+ (((x) >> 24) & 0x000000ff))
+#endif /* CONFIG_CPU_BIG_ENDIAN */
+
+#ifdef __ASSEMBLY__
+#define __emit_inst(x) .long __INSTR_BSWAP(x)
+#else /* __ASSEMBLY__ */
+#define __emit_inst(x) ".long " __stringify(__INSTR_BSWAP(x)) "\n\t"
+#endif /* __ASSEMBLY__ */
+
+#endif /* CONFIG_BROKEN_GAS_INST */
+
+/*
+ * Instructions for modifying PSTATE fields.
+ * As per Arm ARM for v8-A, Section "C.5.1.3 op0 == 0b00, architectural hints,
+ * barriers and CLREX, and PSTATE access", ARM DDI 0487 C.a, system instructions
+ * for accessing PSTATE fields have the following encoding:
+ * Op0 = 0, CRn = 4
+ * Op1, Op2 encodes the PSTATE field modified and defines the constraints.
+ * CRm = Imm4 for the instruction.
+ * Rt = 0x1f
+ */
+#define pstate_field(op1, op2) ((op1) << Op1_shift | (op2) << Op2_shift)
+#define PSTATE_Imm_shift CRm_shift
+
+#define PSTATE_PAN pstate_field(0, 4)
+#define PSTATE_UAO pstate_field(0, 3)
+#define PSTATE_SSBS pstate_field(3, 1)
+#define PSTATE_TCO pstate_field(3, 4)
+
+#define SET_PSTATE_PAN(x) __emit_inst(0xd500401f | PSTATE_PAN | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_UAO(x) __emit_inst(0xd500401f | PSTATE_UAO | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_SSBS(x) __emit_inst(0xd500401f | PSTATE_SSBS | ((!!x) << PSTATE_Imm_shift))
+#define SET_PSTATE_TCO(x) __emit_inst(0xd500401f | PSTATE_TCO | ((!!x) << PSTATE_Imm_shift))
+
+#define set_pstate_pan(x) asm volatile(SET_PSTATE_PAN(x))
+#define set_pstate_uao(x) asm volatile(SET_PSTATE_UAO(x))
+#define set_pstate_ssbs(x) asm volatile(SET_PSTATE_SSBS(x))
+
+#define __SYS_BARRIER_INSN(CRm, op2, Rt) \
+ __emit_inst(0xd5000000 | sys_insn(0, 3, 3, (CRm), (op2)) | ((Rt) & 0x1f))
+
+#define SB_BARRIER_INSN __SYS_BARRIER_INSN(0, 7, 31)
+
+#define SYS_DC_ISW sys_insn(1, 0, 7, 6, 2)
+#define SYS_DC_CSW sys_insn(1, 0, 7, 10, 2)
+#define SYS_DC_CISW sys_insn(1, 0, 7, 14, 2)
+
+/*
+ * System registers, organised loosely by encoding but grouped together
+ * where the architected name contains an index. e.g. ID_MMFR<n>_EL1.
+ */
+#define SYS_OSDTRRX_EL1 sys_reg(2, 0, 0, 0, 2)
+#define SYS_MDCCINT_EL1 sys_reg(2, 0, 0, 2, 0)
+#define SYS_MDSCR_EL1 sys_reg(2, 0, 0, 2, 2)
+#define SYS_OSDTRTX_EL1 sys_reg(2, 0, 0, 3, 2)
+#define SYS_OSECCR_EL1 sys_reg(2, 0, 0, 6, 2)
+#define SYS_DBGBVRn_EL1(n) sys_reg(2, 0, 0, n, 4)
+#define SYS_DBGBCRn_EL1(n) sys_reg(2, 0, 0, n, 5)
+#define SYS_DBGWVRn_EL1(n) sys_reg(2, 0, 0, n, 6)
+#define SYS_DBGWCRn_EL1(n) sys_reg(2, 0, 0, n, 7)
+#define SYS_MDRAR_EL1 sys_reg(2, 0, 1, 0, 0)
+#define SYS_OSLAR_EL1 sys_reg(2, 0, 1, 0, 4)
+#define SYS_OSLSR_EL1 sys_reg(2, 0, 1, 1, 4)
+#define SYS_OSDLR_EL1 sys_reg(2, 0, 1, 3, 4)
+#define SYS_DBGPRCR_EL1 sys_reg(2, 0, 1, 4, 4)
+#define SYS_DBGCLAIMSET_EL1 sys_reg(2, 0, 7, 8, 6)
+#define SYS_DBGCLAIMCLR_EL1 sys_reg(2, 0, 7, 9, 6)
+#define SYS_DBGAUTHSTATUS_EL1 sys_reg(2, 0, 7, 14, 6)
+#define SYS_MDCCSR_EL0 sys_reg(2, 3, 0, 1, 0)
+#define SYS_DBGDTR_EL0 sys_reg(2, 3, 0, 4, 0)
+#define SYS_DBGDTRRX_EL0 sys_reg(2, 3, 0, 5, 0)
+#define SYS_DBGDTRTX_EL0 sys_reg(2, 3, 0, 5, 0)
+#define SYS_DBGVCR32_EL2 sys_reg(2, 4, 0, 7, 0)
+
+#define SYS_MIDR_EL1 sys_reg(3, 0, 0, 0, 0)
+#define SYS_MPIDR_EL1 sys_reg(3, 0, 0, 0, 5)
+#define SYS_REVIDR_EL1 sys_reg(3, 0, 0, 0, 6)
+
+#define SYS_ID_PFR0_EL1 sys_reg(3, 0, 0, 1, 0)
+#define SYS_ID_PFR1_EL1 sys_reg(3, 0, 0, 1, 1)
+#define SYS_ID_PFR2_EL1 sys_reg(3, 0, 0, 3, 4)
+#define SYS_ID_DFR0_EL1 sys_reg(3, 0, 0, 1, 2)
+#define SYS_ID_DFR1_EL1 sys_reg(3, 0, 0, 3, 5)
+#define SYS_ID_AFR0_EL1 sys_reg(3, 0, 0, 1, 3)
+#define SYS_ID_MMFR0_EL1 sys_reg(3, 0, 0, 1, 4)
+#define SYS_ID_MMFR1_EL1 sys_reg(3, 0, 0, 1, 5)
+#define SYS_ID_MMFR2_EL1 sys_reg(3, 0, 0, 1, 6)
+#define SYS_ID_MMFR3_EL1 sys_reg(3, 0, 0, 1, 7)
+#define SYS_ID_MMFR4_EL1 sys_reg(3, 0, 0, 2, 6)
+#define SYS_ID_MMFR5_EL1 sys_reg(3, 0, 0, 3, 6)
+
+#define SYS_ID_ISAR0_EL1 sys_reg(3, 0, 0, 2, 0)
+#define SYS_ID_ISAR1_EL1 sys_reg(3, 0, 0, 2, 1)
+#define SYS_ID_ISAR2_EL1 sys_reg(3, 0, 0, 2, 2)
+#define SYS_ID_ISAR3_EL1 sys_reg(3, 0, 0, 2, 3)
+#define SYS_ID_ISAR4_EL1 sys_reg(3, 0, 0, 2, 4)
+#define SYS_ID_ISAR5_EL1 sys_reg(3, 0, 0, 2, 5)
+#define SYS_ID_ISAR6_EL1 sys_reg(3, 0, 0, 2, 7)
+
+#define SYS_MVFR0_EL1 sys_reg(3, 0, 0, 3, 0)
+#define SYS_MVFR1_EL1 sys_reg(3, 0, 0, 3, 1)
+#define SYS_MVFR2_EL1 sys_reg(3, 0, 0, 3, 2)
+
+#define SYS_ID_AA64PFR0_EL1 sys_reg(3, 0, 0, 4, 0)
+#define SYS_ID_AA64PFR1_EL1 sys_reg(3, 0, 0, 4, 1)
+#define SYS_ID_AA64ZFR0_EL1 sys_reg(3, 0, 0, 4, 4)
+
+#define SYS_ID_AA64DFR0_EL1 sys_reg(3, 0, 0, 5, 0)
+#define SYS_ID_AA64DFR1_EL1 sys_reg(3, 0, 0, 5, 1)
+
+#define SYS_ID_AA64AFR0_EL1 sys_reg(3, 0, 0, 5, 4)
+#define SYS_ID_AA64AFR1_EL1 sys_reg(3, 0, 0, 5, 5)
+
+#define SYS_ID_AA64ISAR0_EL1 sys_reg(3, 0, 0, 6, 0)
+#define SYS_ID_AA64ISAR1_EL1 sys_reg(3, 0, 0, 6, 1)
+
+#define SYS_ID_AA64MMFR0_EL1 sys_reg(3, 0, 0, 7, 0)
+#define SYS_ID_AA64MMFR1_EL1 sys_reg(3, 0, 0, 7, 1)
+#define SYS_ID_AA64MMFR2_EL1 sys_reg(3, 0, 0, 7, 2)
+
+#define SYS_SCTLR_EL1 sys_reg(3, 0, 1, 0, 0)
+#define SYS_ACTLR_EL1 sys_reg(3, 0, 1, 0, 1)
+#define SYS_CPACR_EL1 sys_reg(3, 0, 1, 0, 2)
+#define SYS_RGSR_EL1 sys_reg(3, 0, 1, 0, 5)
+#define SYS_GCR_EL1 sys_reg(3, 0, 1, 0, 6)
+
+#define SYS_ZCR_EL1 sys_reg(3, 0, 1, 2, 0)
+#define SYS_TRFCR_EL1 sys_reg(3, 0, 1, 2, 1)
+
+#define SYS_TTBR0_EL1 sys_reg(3, 0, 2, 0, 0)
+#define SYS_TTBR1_EL1 sys_reg(3, 0, 2, 0, 1)
+#define SYS_TCR_EL1 sys_reg(3, 0, 2, 0, 2)
+
+#define SYS_APIAKEYLO_EL1 sys_reg(3, 0, 2, 1, 0)
+#define SYS_APIAKEYHI_EL1 sys_reg(3, 0, 2, 1, 1)
+#define SYS_APIBKEYLO_EL1 sys_reg(3, 0, 2, 1, 2)
+#define SYS_APIBKEYHI_EL1 sys_reg(3, 0, 2, 1, 3)
+
+#define SYS_APDAKEYLO_EL1 sys_reg(3, 0, 2, 2, 0)
+#define SYS_APDAKEYHI_EL1 sys_reg(3, 0, 2, 2, 1)
+#define SYS_APDBKEYLO_EL1 sys_reg(3, 0, 2, 2, 2)
+#define SYS_APDBKEYHI_EL1 sys_reg(3, 0, 2, 2, 3)
+
+#define SYS_APGAKEYLO_EL1 sys_reg(3, 0, 2, 3, 0)
+#define SYS_APGAKEYHI_EL1 sys_reg(3, 0, 2, 3, 1)
+
+#define SYS_SPSR_EL1 sys_reg(3, 0, 4, 0, 0)
+#define SYS_ELR_EL1 sys_reg(3, 0, 4, 0, 1)
+
+#define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0)
+
+#define SYS_AFSR0_EL1 sys_reg(3, 0, 5, 1, 0)
+#define SYS_AFSR1_EL1 sys_reg(3, 0, 5, 1, 1)
+#define SYS_ESR_EL1 sys_reg(3, 0, 5, 2, 0)
+
+#define SYS_ERRIDR_EL1 sys_reg(3, 0, 5, 3, 0)
+#define SYS_ERRSELR_EL1 sys_reg(3, 0, 5, 3, 1)
+#define SYS_ERXFR_EL1 sys_reg(3, 0, 5, 4, 0)
+#define SYS_ERXCTLR_EL1 sys_reg(3, 0, 5, 4, 1)
+#define SYS_ERXSTATUS_EL1 sys_reg(3, 0, 5, 4, 2)
+#define SYS_ERXADDR_EL1 sys_reg(3, 0, 5, 4, 3)
+#define SYS_ERXMISC0_EL1 sys_reg(3, 0, 5, 5, 0)
+#define SYS_ERXMISC1_EL1 sys_reg(3, 0, 5, 5, 1)
+#define SYS_TFSR_EL1 sys_reg(3, 0, 5, 6, 0)
+#define SYS_TFSRE0_EL1 sys_reg(3, 0, 5, 6, 1)
+
+#define SYS_FAR_EL1 sys_reg(3, 0, 6, 0, 0)
+#define SYS_PAR_EL1 sys_reg(3, 0, 7, 4, 0)
+
+#define SYS_PAR_EL1_F BIT(0)
+#define SYS_PAR_EL1_FST GENMASK(6, 1)
+
+/*** Statistical Profiling Extension ***/
+/* ID registers */
+#define SYS_PMSIDR_EL1 sys_reg(3, 0, 9, 9, 7)
+#define SYS_PMSIDR_EL1_FE_SHIFT 0
+#define SYS_PMSIDR_EL1_FT_SHIFT 1
+#define SYS_PMSIDR_EL1_FL_SHIFT 2
+#define SYS_PMSIDR_EL1_ARCHINST_SHIFT 3
+#define SYS_PMSIDR_EL1_LDS_SHIFT 4
+#define SYS_PMSIDR_EL1_ERND_SHIFT 5
+#define SYS_PMSIDR_EL1_INTERVAL_SHIFT 8
+#define SYS_PMSIDR_EL1_INTERVAL_MASK 0xfUL
+#define SYS_PMSIDR_EL1_MAXSIZE_SHIFT 12
+#define SYS_PMSIDR_EL1_MAXSIZE_MASK 0xfUL
+#define SYS_PMSIDR_EL1_COUNTSIZE_SHIFT 16
+#define SYS_PMSIDR_EL1_COUNTSIZE_MASK 0xfUL
+
+#define SYS_PMBIDR_EL1 sys_reg(3, 0, 9, 10, 7)
+#define SYS_PMBIDR_EL1_ALIGN_SHIFT 0
+#define SYS_PMBIDR_EL1_ALIGN_MASK 0xfU
+#define SYS_PMBIDR_EL1_P_SHIFT 4
+#define SYS_PMBIDR_EL1_F_SHIFT 5
+
+/* Sampling controls */
+#define SYS_PMSCR_EL1 sys_reg(3, 0, 9, 9, 0)
+#define SYS_PMSCR_EL1_E0SPE_SHIFT 0
+#define SYS_PMSCR_EL1_E1SPE_SHIFT 1
+#define SYS_PMSCR_EL1_CX_SHIFT 3
+#define SYS_PMSCR_EL1_PA_SHIFT 4
+#define SYS_PMSCR_EL1_TS_SHIFT 5
+#define SYS_PMSCR_EL1_PCT_SHIFT 6
+
+#define SYS_PMSCR_EL2 sys_reg(3, 4, 9, 9, 0)
+#define SYS_PMSCR_EL2_E0HSPE_SHIFT 0
+#define SYS_PMSCR_EL2_E2SPE_SHIFT 1
+#define SYS_PMSCR_EL2_CX_SHIFT 3
+#define SYS_PMSCR_EL2_PA_SHIFT 4
+#define SYS_PMSCR_EL2_TS_SHIFT 5
+#define SYS_PMSCR_EL2_PCT_SHIFT 6
+
+#define SYS_PMSICR_EL1 sys_reg(3, 0, 9, 9, 2)
+
+#define SYS_PMSIRR_EL1 sys_reg(3, 0, 9, 9, 3)
+#define SYS_PMSIRR_EL1_RND_SHIFT 0
+#define SYS_PMSIRR_EL1_INTERVAL_SHIFT 8
+#define SYS_PMSIRR_EL1_INTERVAL_MASK 0xffffffUL
+
+/* Filtering controls */
+#define SYS_PMSNEVFR_EL1 sys_reg(3, 0, 9, 9, 1)
+
+#define SYS_PMSFCR_EL1 sys_reg(3, 0, 9, 9, 4)
+#define SYS_PMSFCR_EL1_FE_SHIFT 0
+#define SYS_PMSFCR_EL1_FT_SHIFT 1
+#define SYS_PMSFCR_EL1_FL_SHIFT 2
+#define SYS_PMSFCR_EL1_B_SHIFT 16
+#define SYS_PMSFCR_EL1_LD_SHIFT 17
+#define SYS_PMSFCR_EL1_ST_SHIFT 18
+
+#define SYS_PMSEVFR_EL1 sys_reg(3, 0, 9, 9, 5)
+#define SYS_PMSEVFR_EL1_RES0_8_2 \
+ (GENMASK_ULL(47, 32) | GENMASK_ULL(23, 16) | GENMASK_ULL(11, 8) |\
+ BIT_ULL(6) | BIT_ULL(4) | BIT_ULL(2) | BIT_ULL(0))
+#define SYS_PMSEVFR_EL1_RES0_8_3 \
+ (SYS_PMSEVFR_EL1_RES0_8_2 & ~(BIT_ULL(18) | BIT_ULL(17) | BIT_ULL(11)))
+
+#define SYS_PMSLATFR_EL1 sys_reg(3, 0, 9, 9, 6)
+#define SYS_PMSLATFR_EL1_MINLAT_SHIFT 0
+
+/* Buffer controls */
+#define SYS_PMBLIMITR_EL1 sys_reg(3, 0, 9, 10, 0)
+#define SYS_PMBLIMITR_EL1_E_SHIFT 0
+#define SYS_PMBLIMITR_EL1_FM_SHIFT 1
+#define SYS_PMBLIMITR_EL1_FM_MASK 0x3UL
+#define SYS_PMBLIMITR_EL1_FM_STOP_IRQ (0 << SYS_PMBLIMITR_EL1_FM_SHIFT)
+
+#define SYS_PMBPTR_EL1 sys_reg(3, 0, 9, 10, 1)
+
+/* Buffer error reporting */
+#define SYS_PMBSR_EL1 sys_reg(3, 0, 9, 10, 3)
+#define SYS_PMBSR_EL1_COLL_SHIFT 16
+#define SYS_PMBSR_EL1_S_SHIFT 17
+#define SYS_PMBSR_EL1_EA_SHIFT 18
+#define SYS_PMBSR_EL1_DL_SHIFT 19
+#define SYS_PMBSR_EL1_EC_SHIFT 26
+#define SYS_PMBSR_EL1_EC_MASK 0x3fUL
+
+#define SYS_PMBSR_EL1_EC_BUF (0x0UL << SYS_PMBSR_EL1_EC_SHIFT)
+#define SYS_PMBSR_EL1_EC_FAULT_S1 (0x24UL << SYS_PMBSR_EL1_EC_SHIFT)
+#define SYS_PMBSR_EL1_EC_FAULT_S2 (0x25UL << SYS_PMBSR_EL1_EC_SHIFT)
+
+#define SYS_PMBSR_EL1_FAULT_FSC_SHIFT 0
+#define SYS_PMBSR_EL1_FAULT_FSC_MASK 0x3fUL
+
+#define SYS_PMBSR_EL1_BUF_BSC_SHIFT 0
+#define SYS_PMBSR_EL1_BUF_BSC_MASK 0x3fUL
+
+#define SYS_PMBSR_EL1_BUF_BSC_FULL (0x1UL << SYS_PMBSR_EL1_BUF_BSC_SHIFT)
+
+/*** End of Statistical Profiling Extension ***/
+
+/*
+ * TRBE Registers
+ */
+#define SYS_TRBLIMITR_EL1 sys_reg(3, 0, 9, 11, 0)
+#define SYS_TRBPTR_EL1 sys_reg(3, 0, 9, 11, 1)
+#define SYS_TRBBASER_EL1 sys_reg(3, 0, 9, 11, 2)
+#define SYS_TRBSR_EL1 sys_reg(3, 0, 9, 11, 3)
+#define SYS_TRBMAR_EL1 sys_reg(3, 0, 9, 11, 4)
+#define SYS_TRBTRG_EL1 sys_reg(3, 0, 9, 11, 6)
+#define SYS_TRBIDR_EL1 sys_reg(3, 0, 9, 11, 7)
+
+#define TRBLIMITR_LIMIT_MASK GENMASK_ULL(51, 0)
+#define TRBLIMITR_LIMIT_SHIFT 12
+#define TRBLIMITR_NVM BIT(5)
+#define TRBLIMITR_TRIG_MODE_MASK GENMASK(1, 0)
+#define TRBLIMITR_TRIG_MODE_SHIFT 3
+#define TRBLIMITR_FILL_MODE_MASK GENMASK(1, 0)
+#define TRBLIMITR_FILL_MODE_SHIFT 1
+#define TRBLIMITR_ENABLE BIT(0)
+#define TRBPTR_PTR_MASK GENMASK_ULL(63, 0)
+#define TRBPTR_PTR_SHIFT 0
+#define TRBBASER_BASE_MASK GENMASK_ULL(51, 0)
+#define TRBBASER_BASE_SHIFT 12
+#define TRBSR_EC_MASK GENMASK(5, 0)
+#define TRBSR_EC_SHIFT 26
+#define TRBSR_IRQ BIT(22)
+#define TRBSR_TRG BIT(21)
+#define TRBSR_WRAP BIT(20)
+#define TRBSR_ABORT BIT(18)
+#define TRBSR_STOP BIT(17)
+#define TRBSR_MSS_MASK GENMASK(15, 0)
+#define TRBSR_MSS_SHIFT 0
+#define TRBSR_BSC_MASK GENMASK(5, 0)
+#define TRBSR_BSC_SHIFT 0
+#define TRBSR_FSC_MASK GENMASK(5, 0)
+#define TRBSR_FSC_SHIFT 0
+#define TRBMAR_SHARE_MASK GENMASK(1, 0)
+#define TRBMAR_SHARE_SHIFT 8
+#define TRBMAR_OUTER_MASK GENMASK(3, 0)
+#define TRBMAR_OUTER_SHIFT 4
+#define TRBMAR_INNER_MASK GENMASK(3, 0)
+#define TRBMAR_INNER_SHIFT 0
+#define TRBTRG_TRG_MASK GENMASK(31, 0)
+#define TRBTRG_TRG_SHIFT 0
+#define TRBIDR_FLAG BIT(5)
+#define TRBIDR_PROG BIT(4)
+#define TRBIDR_ALIGN_MASK GENMASK(3, 0)
+#define TRBIDR_ALIGN_SHIFT 0
+
+#define SYS_PMINTENSET_EL1 sys_reg(3, 0, 9, 14, 1)
+#define SYS_PMINTENCLR_EL1 sys_reg(3, 0, 9, 14, 2)
+
+#define SYS_PMMIR_EL1 sys_reg(3, 0, 9, 14, 6)
+
+#define SYS_MAIR_EL1 sys_reg(3, 0, 10, 2, 0)
+#define SYS_AMAIR_EL1 sys_reg(3, 0, 10, 3, 0)
+
+#define SYS_LORSA_EL1 sys_reg(3, 0, 10, 4, 0)
+#define SYS_LOREA_EL1 sys_reg(3, 0, 10, 4, 1)
+#define SYS_LORN_EL1 sys_reg(3, 0, 10, 4, 2)
+#define SYS_LORC_EL1 sys_reg(3, 0, 10, 4, 3)
+#define SYS_LORID_EL1 sys_reg(3, 0, 10, 4, 7)
+
+#define SYS_VBAR_EL1 sys_reg(3, 0, 12, 0, 0)
+#define SYS_DISR_EL1 sys_reg(3, 0, 12, 1, 1)
+
+#define SYS_ICC_IAR0_EL1 sys_reg(3, 0, 12, 8, 0)
+#define SYS_ICC_EOIR0_EL1 sys_reg(3, 0, 12, 8, 1)
+#define SYS_ICC_HPPIR0_EL1 sys_reg(3, 0, 12, 8, 2)
+#define SYS_ICC_BPR0_EL1 sys_reg(3, 0, 12, 8, 3)
+#define SYS_ICC_AP0Rn_EL1(n) sys_reg(3, 0, 12, 8, 4 | n)
+#define SYS_ICC_AP0R0_EL1 SYS_ICC_AP0Rn_EL1(0)
+#define SYS_ICC_AP0R1_EL1 SYS_ICC_AP0Rn_EL1(1)
+#define SYS_ICC_AP0R2_EL1 SYS_ICC_AP0Rn_EL1(2)
+#define SYS_ICC_AP0R3_EL1 SYS_ICC_AP0Rn_EL1(3)
+#define SYS_ICC_AP1Rn_EL1(n) sys_reg(3, 0, 12, 9, n)
+#define SYS_ICC_AP1R0_EL1 SYS_ICC_AP1Rn_EL1(0)
+#define SYS_ICC_AP1R1_EL1 SYS_ICC_AP1Rn_EL1(1)
+#define SYS_ICC_AP1R2_EL1 SYS_ICC_AP1Rn_EL1(2)
+#define SYS_ICC_AP1R3_EL1 SYS_ICC_AP1Rn_EL1(3)
+#define SYS_ICC_DIR_EL1 sys_reg(3, 0, 12, 11, 1)
+#define SYS_ICC_RPR_EL1 sys_reg(3, 0, 12, 11, 3)
+#define SYS_ICC_SGI1R_EL1 sys_reg(3, 0, 12, 11, 5)
+#define SYS_ICC_ASGI1R_EL1 sys_reg(3, 0, 12, 11, 6)
+#define SYS_ICC_SGI0R_EL1 sys_reg(3, 0, 12, 11, 7)
+#define SYS_ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0)
+#define SYS_ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1)
+#define SYS_ICC_HPPIR1_EL1 sys_reg(3, 0, 12, 12, 2)
+#define SYS_ICC_BPR1_EL1 sys_reg(3, 0, 12, 12, 3)
+#define SYS_ICC_CTLR_EL1 sys_reg(3, 0, 12, 12, 4)
+#define SYS_ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5)
+#define SYS_ICC_IGRPEN0_EL1 sys_reg(3, 0, 12, 12, 6)
+#define SYS_ICC_IGRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)
+
+#define SYS_CONTEXTIDR_EL1 sys_reg(3, 0, 13, 0, 1)
+#define SYS_TPIDR_EL1 sys_reg(3, 0, 13, 0, 4)
+
+#define SYS_SCXTNUM_EL1 sys_reg(3, 0, 13, 0, 7)
+
+#define SYS_CNTKCTL_EL1 sys_reg(3, 0, 14, 1, 0)
+
+#define SYS_CCSIDR_EL1 sys_reg(3, 1, 0, 0, 0)
+#define SYS_CLIDR_EL1 sys_reg(3, 1, 0, 0, 1)
+#define SYS_GMID_EL1 sys_reg(3, 1, 0, 0, 4)
+#define SYS_AIDR_EL1 sys_reg(3, 1, 0, 0, 7)
+
+#define SYS_CSSELR_EL1 sys_reg(3, 2, 0, 0, 0)
+
+#define SYS_CTR_EL0 sys_reg(3, 3, 0, 0, 1)
+#define SYS_DCZID_EL0 sys_reg(3, 3, 0, 0, 7)
+
+#define SYS_RNDR_EL0 sys_reg(3, 3, 2, 4, 0)
+#define SYS_RNDRRS_EL0 sys_reg(3, 3, 2, 4, 1)
+
+#define SYS_PMCR_EL0 sys_reg(3, 3, 9, 12, 0)
+#define SYS_PMCNTENSET_EL0 sys_reg(3, 3, 9, 12, 1)
+#define SYS_PMCNTENCLR_EL0 sys_reg(3, 3, 9, 12, 2)
+#define SYS_PMOVSCLR_EL0 sys_reg(3, 3, 9, 12, 3)
+#define SYS_PMSWINC_EL0 sys_reg(3, 3, 9, 12, 4)
+#define SYS_PMSELR_EL0 sys_reg(3, 3, 9, 12, 5)
+#define SYS_PMCEID0_EL0 sys_reg(3, 3, 9, 12, 6)
+#define SYS_PMCEID1_EL0 sys_reg(3, 3, 9, 12, 7)
+#define SYS_PMCCNTR_EL0 sys_reg(3, 3, 9, 13, 0)
+#define SYS_PMXEVTYPER_EL0 sys_reg(3, 3, 9, 13, 1)
+#define SYS_PMXEVCNTR_EL0 sys_reg(3, 3, 9, 13, 2)
+#define SYS_PMUSERENR_EL0 sys_reg(3, 3, 9, 14, 0)
+#define SYS_PMOVSSET_EL0 sys_reg(3, 3, 9, 14, 3)
+
+#define SYS_TPIDR_EL0 sys_reg(3, 3, 13, 0, 2)
+#define SYS_TPIDRRO_EL0 sys_reg(3, 3, 13, 0, 3)
+
+#define SYS_SCXTNUM_EL0 sys_reg(3, 3, 13, 0, 7)
+
+/* Definitions for system register interface to AMU for ARMv8.4 onwards */
+#define SYS_AM_EL0(crm, op2) sys_reg(3, 3, 13, (crm), (op2))
+#define SYS_AMCR_EL0 SYS_AM_EL0(2, 0)
+#define SYS_AMCFGR_EL0 SYS_AM_EL0(2, 1)
+#define SYS_AMCGCR_EL0 SYS_AM_EL0(2, 2)
+#define SYS_AMUSERENR_EL0 SYS_AM_EL0(2, 3)
+#define SYS_AMCNTENCLR0_EL0 SYS_AM_EL0(2, 4)
+#define SYS_AMCNTENSET0_EL0 SYS_AM_EL0(2, 5)
+#define SYS_AMCNTENCLR1_EL0 SYS_AM_EL0(3, 0)
+#define SYS_AMCNTENSET1_EL0 SYS_AM_EL0(3, 1)
+
+/*
+ * Group 0 of activity monitors (architected):
+ * op0 op1 CRn CRm op2
+ * Counter: 11 011 1101 010:n<3> n<2:0>
+ * Type: 11 011 1101 011:n<3> n<2:0>
+ * n: 0-15
+ *
+ * Group 1 of activity monitors (auxiliary):
+ * op0 op1 CRn CRm op2
+ * Counter: 11 011 1101 110:n<3> n<2:0>
+ * Type: 11 011 1101 111:n<3> n<2:0>
+ * n: 0-15
+ */
+
+#define SYS_AMEVCNTR0_EL0(n) SYS_AM_EL0(4 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPER0_EL0(n) SYS_AM_EL0(6 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVCNTR1_EL0(n) SYS_AM_EL0(12 + ((n) >> 3), (n) & 7)
+#define SYS_AMEVTYPER1_EL0(n) SYS_AM_EL0(14 + ((n) >> 3), (n) & 7)
+
+/* AMU v1: Fixed (architecturally defined) activity monitors */
+#define SYS_AMEVCNTR0_CORE_EL0 SYS_AMEVCNTR0_EL0(0)
+#define SYS_AMEVCNTR0_CONST_EL0 SYS_AMEVCNTR0_EL0(1)
+#define SYS_AMEVCNTR0_INST_RET_EL0 SYS_AMEVCNTR0_EL0(2)
+#define SYS_AMEVCNTR0_MEM_STALL SYS_AMEVCNTR0_EL0(3)
+
+#define SYS_CNTFRQ_EL0 sys_reg(3, 3, 14, 0, 0)
+
+#define SYS_CNTP_TVAL_EL0 sys_reg(3, 3, 14, 2, 0)
+#define SYS_CNTP_CTL_EL0 sys_reg(3, 3, 14, 2, 1)
+#define SYS_CNTP_CVAL_EL0 sys_reg(3, 3, 14, 2, 2)
+
+#define SYS_CNTV_CTL_EL0 sys_reg(3, 3, 14, 3, 1)
+#define SYS_CNTV_CVAL_EL0 sys_reg(3, 3, 14, 3, 2)
+
+#define SYS_AARCH32_CNTP_TVAL sys_reg(0, 0, 14, 2, 0)
+#define SYS_AARCH32_CNTP_CTL sys_reg(0, 0, 14, 2, 1)
+#define SYS_AARCH32_CNTP_CVAL sys_reg(0, 2, 0, 14, 0)
+
+#define __PMEV_op2(n) ((n) & 0x7)
+#define __CNTR_CRm(n) (0x8 | (((n) >> 3) & 0x3))
+#define SYS_PMEVCNTRn_EL0(n) sys_reg(3, 3, 14, __CNTR_CRm(n), __PMEV_op2(n))
+#define __TYPER_CRm(n) (0xc | (((n) >> 3) & 0x3))
+#define SYS_PMEVTYPERn_EL0(n) sys_reg(3, 3, 14, __TYPER_CRm(n), __PMEV_op2(n))
+
+#define SYS_PMCCFILTR_EL0 sys_reg(3, 3, 14, 15, 7)
+
+#define SYS_SCTLR_EL2 sys_reg(3, 4, 1, 0, 0)
+#define SYS_HFGRTR_EL2 sys_reg(3, 4, 1, 1, 4)
+#define SYS_HFGWTR_EL2 sys_reg(3, 4, 1, 1, 5)
+#define SYS_HFGITR_EL2 sys_reg(3, 4, 1, 1, 6)
+#define SYS_ZCR_EL2 sys_reg(3, 4, 1, 2, 0)
+#define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1)
+#define SYS_DACR32_EL2 sys_reg(3, 4, 3, 0, 0)
+#define SYS_HDFGRTR_EL2 sys_reg(3, 4, 3, 1, 4)
+#define SYS_HDFGWTR_EL2 sys_reg(3, 4, 3, 1, 5)
+#define SYS_HAFGRTR_EL2 sys_reg(3, 4, 3, 1, 6)
+#define SYS_SPSR_EL2 sys_reg(3, 4, 4, 0, 0)
+#define SYS_ELR_EL2 sys_reg(3, 4, 4, 0, 1)
+#define SYS_IFSR32_EL2 sys_reg(3, 4, 5, 0, 1)
+#define SYS_ESR_EL2 sys_reg(3, 4, 5, 2, 0)
+#define SYS_VSESR_EL2 sys_reg(3, 4, 5, 2, 3)
+#define SYS_FPEXC32_EL2 sys_reg(3, 4, 5, 3, 0)
+#define SYS_TFSR_EL2 sys_reg(3, 4, 5, 6, 0)
+#define SYS_FAR_EL2 sys_reg(3, 4, 6, 0, 0)
+
+#define SYS_VDISR_EL2 sys_reg(3, 4, 12, 1, 1)
+#define __SYS__AP0Rx_EL2(x) sys_reg(3, 4, 12, 8, x)
+#define SYS_ICH_AP0R0_EL2 __SYS__AP0Rx_EL2(0)
+#define SYS_ICH_AP0R1_EL2 __SYS__AP0Rx_EL2(1)
+#define SYS_ICH_AP0R2_EL2 __SYS__AP0Rx_EL2(2)
+#define SYS_ICH_AP0R3_EL2 __SYS__AP0Rx_EL2(3)
+
+#define __SYS__AP1Rx_EL2(x) sys_reg(3, 4, 12, 9, x)
+#define SYS_ICH_AP1R0_EL2 __SYS__AP1Rx_EL2(0)
+#define SYS_ICH_AP1R1_EL2 __SYS__AP1Rx_EL2(1)
+#define SYS_ICH_AP1R2_EL2 __SYS__AP1Rx_EL2(2)
+#define SYS_ICH_AP1R3_EL2 __SYS__AP1Rx_EL2(3)
+
+#define SYS_ICH_VSEIR_EL2 sys_reg(3, 4, 12, 9, 4)
+#define SYS_ICC_SRE_EL2 sys_reg(3, 4, 12, 9, 5)
+#define SYS_ICH_HCR_EL2 sys_reg(3, 4, 12, 11, 0)
+#define SYS_ICH_VTR_EL2 sys_reg(3, 4, 12, 11, 1)
+#define SYS_ICH_MISR_EL2 sys_reg(3, 4, 12, 11, 2)
+#define SYS_ICH_EISR_EL2 sys_reg(3, 4, 12, 11, 3)
+#define SYS_ICH_ELRSR_EL2 sys_reg(3, 4, 12, 11, 5)
+#define SYS_ICH_VMCR_EL2 sys_reg(3, 4, 12, 11, 7)
+
+#define __SYS__LR0_EL2(x) sys_reg(3, 4, 12, 12, x)
+#define SYS_ICH_LR0_EL2 __SYS__LR0_EL2(0)
+#define SYS_ICH_LR1_EL2 __SYS__LR0_EL2(1)
+#define SYS_ICH_LR2_EL2 __SYS__LR0_EL2(2)
+#define SYS_ICH_LR3_EL2 __SYS__LR0_EL2(3)
+#define SYS_ICH_LR4_EL2 __SYS__LR0_EL2(4)
+#define SYS_ICH_LR5_EL2 __SYS__LR0_EL2(5)
+#define SYS_ICH_LR6_EL2 __SYS__LR0_EL2(6)
+#define SYS_ICH_LR7_EL2 __SYS__LR0_EL2(7)
+
+#define __SYS__LR8_EL2(x) sys_reg(3, 4, 12, 13, x)
+#define SYS_ICH_LR8_EL2 __SYS__LR8_EL2(0)
+#define SYS_ICH_LR9_EL2 __SYS__LR8_EL2(1)
+#define SYS_ICH_LR10_EL2 __SYS__LR8_EL2(2)
+#define SYS_ICH_LR11_EL2 __SYS__LR8_EL2(3)
+#define SYS_ICH_LR12_EL2 __SYS__LR8_EL2(4)
+#define SYS_ICH_LR13_EL2 __SYS__LR8_EL2(5)
+#define SYS_ICH_LR14_EL2 __SYS__LR8_EL2(6)
+#define SYS_ICH_LR15_EL2 __SYS__LR8_EL2(7)
+
+/* VHE encodings for architectural EL0/1 system registers */
+#define SYS_SCTLR_EL12 sys_reg(3, 5, 1, 0, 0)
+#define SYS_CPACR_EL12 sys_reg(3, 5, 1, 0, 2)
+#define SYS_ZCR_EL12 sys_reg(3, 5, 1, 2, 0)
+#define SYS_TTBR0_EL12 sys_reg(3, 5, 2, 0, 0)
+#define SYS_TTBR1_EL12 sys_reg(3, 5, 2, 0, 1)
+#define SYS_TCR_EL12 sys_reg(3, 5, 2, 0, 2)
+#define SYS_SPSR_EL12 sys_reg(3, 5, 4, 0, 0)
+#define SYS_ELR_EL12 sys_reg(3, 5, 4, 0, 1)
+#define SYS_AFSR0_EL12 sys_reg(3, 5, 5, 1, 0)
+#define SYS_AFSR1_EL12 sys_reg(3, 5, 5, 1, 1)
+#define SYS_ESR_EL12 sys_reg(3, 5, 5, 2, 0)
+#define SYS_TFSR_EL12 sys_reg(3, 5, 5, 6, 0)
+#define SYS_FAR_EL12 sys_reg(3, 5, 6, 0, 0)
+#define SYS_MAIR_EL12 sys_reg(3, 5, 10, 2, 0)
+#define SYS_AMAIR_EL12 sys_reg(3, 5, 10, 3, 0)
+#define SYS_VBAR_EL12 sys_reg(3, 5, 12, 0, 0)
+#define SYS_CONTEXTIDR_EL12 sys_reg(3, 5, 13, 0, 1)
+#define SYS_CNTKCTL_EL12 sys_reg(3, 5, 14, 1, 0)
+#define SYS_CNTP_TVAL_EL02 sys_reg(3, 5, 14, 2, 0)
+#define SYS_CNTP_CTL_EL02 sys_reg(3, 5, 14, 2, 1)
+#define SYS_CNTP_CVAL_EL02 sys_reg(3, 5, 14, 2, 2)
+#define SYS_CNTV_TVAL_EL02 sys_reg(3, 5, 14, 3, 0)
+#define SYS_CNTV_CTL_EL02 sys_reg(3, 5, 14, 3, 1)
+#define SYS_CNTV_CVAL_EL02 sys_reg(3, 5, 14, 3, 2)
+
+/* Common SCTLR_ELx flags. */
+#define SCTLR_ELx_DSSBS (BIT(44))
+#define SCTLR_ELx_ATA (BIT(43))
+
+#define SCTLR_ELx_TCF_SHIFT 40
+#define SCTLR_ELx_TCF_NONE (UL(0x0) << SCTLR_ELx_TCF_SHIFT)
+#define SCTLR_ELx_TCF_SYNC (UL(0x1) << SCTLR_ELx_TCF_SHIFT)
+#define SCTLR_ELx_TCF_ASYNC (UL(0x2) << SCTLR_ELx_TCF_SHIFT)
+#define SCTLR_ELx_TCF_MASK (UL(0x3) << SCTLR_ELx_TCF_SHIFT)
+
+#define SCTLR_ELx_ENIA_SHIFT 31
+
+#define SCTLR_ELx_ITFSB (BIT(37))
+#define SCTLR_ELx_ENIA (BIT(SCTLR_ELx_ENIA_SHIFT))
+#define SCTLR_ELx_ENIB (BIT(30))
+#define SCTLR_ELx_ENDA (BIT(27))
+#define SCTLR_ELx_EE (BIT(25))
+#define SCTLR_ELx_IESB (BIT(21))
+#define SCTLR_ELx_WXN (BIT(19))
+#define SCTLR_ELx_ENDB (BIT(13))
+#define SCTLR_ELx_I (BIT(12))
+#define SCTLR_ELx_SA (BIT(3))
+#define SCTLR_ELx_C (BIT(2))
+#define SCTLR_ELx_A (BIT(1))
+#define SCTLR_ELx_M (BIT(0))
+
+/* SCTLR_EL2 specific flags. */
+#define SCTLR_EL2_RES1 ((BIT(4)) | (BIT(5)) | (BIT(11)) | (BIT(16)) | \
+ (BIT(18)) | (BIT(22)) | (BIT(23)) | (BIT(28)) | \
+ (BIT(29)))
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define ENDIAN_SET_EL2 SCTLR_ELx_EE
+#else
+#define ENDIAN_SET_EL2 0
+#endif
+
+#define INIT_SCTLR_EL2_MMU_ON \
+ (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_ELx_I | \
+ SCTLR_ELx_IESB | SCTLR_ELx_WXN | ENDIAN_SET_EL2 | \
+ SCTLR_ELx_ITFSB | SCTLR_EL2_RES1)
+
+#define INIT_SCTLR_EL2_MMU_OFF \
+ (SCTLR_EL2_RES1 | ENDIAN_SET_EL2)
+
+/* SCTLR_EL1 specific flags. */
+#define SCTLR_EL1_EPAN (BIT(57))
+#define SCTLR_EL1_ATA0 (BIT(42))
+
+#define SCTLR_EL1_TCF0_SHIFT 38
+#define SCTLR_EL1_TCF0_NONE (UL(0x0) << SCTLR_EL1_TCF0_SHIFT)
+#define SCTLR_EL1_TCF0_SYNC (UL(0x1) << SCTLR_EL1_TCF0_SHIFT)
+#define SCTLR_EL1_TCF0_ASYNC (UL(0x2) << SCTLR_EL1_TCF0_SHIFT)
+#define SCTLR_EL1_TCF0_MASK (UL(0x3) << SCTLR_EL1_TCF0_SHIFT)
+
+#define SCTLR_EL1_BT1 (BIT(36))
+#define SCTLR_EL1_BT0 (BIT(35))
+#define SCTLR_EL1_UCI (BIT(26))
+#define SCTLR_EL1_E0E (BIT(24))
+#define SCTLR_EL1_SPAN (BIT(23))
+#define SCTLR_EL1_NTWE (BIT(18))
+#define SCTLR_EL1_NTWI (BIT(16))
+#define SCTLR_EL1_UCT (BIT(15))
+#define SCTLR_EL1_DZE (BIT(14))
+#define SCTLR_EL1_UMA (BIT(9))
+#define SCTLR_EL1_SED (BIT(8))
+#define SCTLR_EL1_ITD (BIT(7))
+#define SCTLR_EL1_CP15BEN (BIT(5))
+#define SCTLR_EL1_SA0 (BIT(4))
+
+#define SCTLR_EL1_RES1 ((BIT(11)) | (BIT(20)) | (BIT(22)) | (BIT(28)) | \
+ (BIT(29)))
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define ENDIAN_SET_EL1 (SCTLR_EL1_E0E | SCTLR_ELx_EE)
+#else
+#define ENDIAN_SET_EL1 0
+#endif
+
+#define INIT_SCTLR_EL1_MMU_OFF \
+ (ENDIAN_SET_EL1 | SCTLR_EL1_RES1)
+
+#define INIT_SCTLR_EL1_MMU_ON \
+ (SCTLR_ELx_M | SCTLR_ELx_C | SCTLR_ELx_SA | SCTLR_EL1_SA0 | \
+ SCTLR_EL1_SED | SCTLR_ELx_I | SCTLR_EL1_DZE | SCTLR_EL1_UCT | \
+ SCTLR_EL1_NTWE | SCTLR_ELx_IESB | SCTLR_EL1_SPAN | SCTLR_ELx_ITFSB | \
+ SCTLR_ELx_ATA | SCTLR_EL1_ATA0 | ENDIAN_SET_EL1 | SCTLR_EL1_UCI | \
+ SCTLR_EL1_EPAN | SCTLR_EL1_RES1)
+
+/* MAIR_ELx memory attributes (used by Linux) */
+#define MAIR_ATTR_DEVICE_nGnRnE UL(0x00)
+#define MAIR_ATTR_DEVICE_nGnRE UL(0x04)
+#define MAIR_ATTR_NORMAL_NC UL(0x44)
+#define MAIR_ATTR_NORMAL_TAGGED UL(0xf0)
+#define MAIR_ATTR_NORMAL UL(0xff)
+#define MAIR_ATTR_MASK UL(0xff)
+
+/* Position the attr at the correct index */
+#define MAIR_ATTRIDX(attr, idx) ((attr) << ((idx) * 8))
+
+/* id_aa64isar0 */
+#define ID_AA64ISAR0_RNDR_SHIFT 60
+#define ID_AA64ISAR0_TLB_SHIFT 56
+#define ID_AA64ISAR0_TS_SHIFT 52
+#define ID_AA64ISAR0_FHM_SHIFT 48
+#define ID_AA64ISAR0_DP_SHIFT 44
+#define ID_AA64ISAR0_SM4_SHIFT 40
+#define ID_AA64ISAR0_SM3_SHIFT 36
+#define ID_AA64ISAR0_SHA3_SHIFT 32
+#define ID_AA64ISAR0_RDM_SHIFT 28
+#define ID_AA64ISAR0_ATOMICS_SHIFT 20
+#define ID_AA64ISAR0_CRC32_SHIFT 16
+#define ID_AA64ISAR0_SHA2_SHIFT 12
+#define ID_AA64ISAR0_SHA1_SHIFT 8
+#define ID_AA64ISAR0_AES_SHIFT 4
+
+#define ID_AA64ISAR0_TLB_RANGE_NI 0x0
+#define ID_AA64ISAR0_TLB_RANGE 0x2
+
+/* id_aa64isar1 */
+#define ID_AA64ISAR1_I8MM_SHIFT 52
+#define ID_AA64ISAR1_DGH_SHIFT 48
+#define ID_AA64ISAR1_BF16_SHIFT 44
+#define ID_AA64ISAR1_SPECRES_SHIFT 40
+#define ID_AA64ISAR1_SB_SHIFT 36
+#define ID_AA64ISAR1_FRINTTS_SHIFT 32
+#define ID_AA64ISAR1_GPI_SHIFT 28
+#define ID_AA64ISAR1_GPA_SHIFT 24
+#define ID_AA64ISAR1_LRCPC_SHIFT 20
+#define ID_AA64ISAR1_FCMA_SHIFT 16
+#define ID_AA64ISAR1_JSCVT_SHIFT 12
+#define ID_AA64ISAR1_API_SHIFT 8
+#define ID_AA64ISAR1_APA_SHIFT 4
+#define ID_AA64ISAR1_DPB_SHIFT 0
+
+#define ID_AA64ISAR1_APA_NI 0x0
+#define ID_AA64ISAR1_APA_ARCHITECTED 0x1
+#define ID_AA64ISAR1_APA_ARCH_EPAC 0x2
+#define ID_AA64ISAR1_APA_ARCH_EPAC2 0x3
+#define ID_AA64ISAR1_APA_ARCH_EPAC2_FPAC 0x4
+#define ID_AA64ISAR1_APA_ARCH_EPAC2_FPAC_CMB 0x5
+#define ID_AA64ISAR1_API_NI 0x0
+#define ID_AA64ISAR1_API_IMP_DEF 0x1
+#define ID_AA64ISAR1_API_IMP_DEF_EPAC 0x2
+#define ID_AA64ISAR1_API_IMP_DEF_EPAC2 0x3
+#define ID_AA64ISAR1_API_IMP_DEF_EPAC2_FPAC 0x4
+#define ID_AA64ISAR1_API_IMP_DEF_EPAC2_FPAC_CMB 0x5
+#define ID_AA64ISAR1_GPA_NI 0x0
+#define ID_AA64ISAR1_GPA_ARCHITECTED 0x1
+#define ID_AA64ISAR1_GPI_NI 0x0
+#define ID_AA64ISAR1_GPI_IMP_DEF 0x1
+
+/* id_aa64pfr0 */
+#define ID_AA64PFR0_CSV3_SHIFT 60
+#define ID_AA64PFR0_CSV2_SHIFT 56
+#define ID_AA64PFR0_DIT_SHIFT 48
+#define ID_AA64PFR0_AMU_SHIFT 44
+#define ID_AA64PFR0_MPAM_SHIFT 40
+#define ID_AA64PFR0_SEL2_SHIFT 36
+#define ID_AA64PFR0_SVE_SHIFT 32
+#define ID_AA64PFR0_RAS_SHIFT 28
+#define ID_AA64PFR0_GIC_SHIFT 24
+#define ID_AA64PFR0_ASIMD_SHIFT 20
+#define ID_AA64PFR0_FP_SHIFT 16
+#define ID_AA64PFR0_EL3_SHIFT 12
+#define ID_AA64PFR0_EL2_SHIFT 8
+#define ID_AA64PFR0_EL1_SHIFT 4
+#define ID_AA64PFR0_EL0_SHIFT 0
+
+#define ID_AA64PFR0_AMU 0x1
+#define ID_AA64PFR0_SVE 0x1
+#define ID_AA64PFR0_RAS_V1 0x1
+#define ID_AA64PFR0_RAS_V1P1 0x2
+#define ID_AA64PFR0_FP_NI 0xf
+#define ID_AA64PFR0_FP_SUPPORTED 0x0
+#define ID_AA64PFR0_ASIMD_NI 0xf
+#define ID_AA64PFR0_ASIMD_SUPPORTED 0x0
+#define ID_AA64PFR0_ELx_64BIT_ONLY 0x1
+#define ID_AA64PFR0_ELx_32BIT_64BIT 0x2
+
+/* id_aa64pfr1 */
+#define ID_AA64PFR1_MPAMFRAC_SHIFT 16
+#define ID_AA64PFR1_RASFRAC_SHIFT 12
+#define ID_AA64PFR1_MTE_SHIFT 8
+#define ID_AA64PFR1_SSBS_SHIFT 4
+#define ID_AA64PFR1_BT_SHIFT 0
+
+#define ID_AA64PFR1_SSBS_PSTATE_NI 0
+#define ID_AA64PFR1_SSBS_PSTATE_ONLY 1
+#define ID_AA64PFR1_SSBS_PSTATE_INSNS 2
+#define ID_AA64PFR1_BT_BTI 0x1
+
+#define ID_AA64PFR1_MTE_NI 0x0
+#define ID_AA64PFR1_MTE_EL0 0x1
+#define ID_AA64PFR1_MTE 0x2
+
+/* id_aa64zfr0 */
+#define ID_AA64ZFR0_F64MM_SHIFT 56
+#define ID_AA64ZFR0_F32MM_SHIFT 52
+#define ID_AA64ZFR0_I8MM_SHIFT 44
+#define ID_AA64ZFR0_SM4_SHIFT 40
+#define ID_AA64ZFR0_SHA3_SHIFT 32
+#define ID_AA64ZFR0_BF16_SHIFT 20
+#define ID_AA64ZFR0_BITPERM_SHIFT 16
+#define ID_AA64ZFR0_AES_SHIFT 4
+#define ID_AA64ZFR0_SVEVER_SHIFT 0
+
+#define ID_AA64ZFR0_F64MM 0x1
+#define ID_AA64ZFR0_F32MM 0x1
+#define ID_AA64ZFR0_I8MM 0x1
+#define ID_AA64ZFR0_BF16 0x1
+#define ID_AA64ZFR0_SM4 0x1
+#define ID_AA64ZFR0_SHA3 0x1
+#define ID_AA64ZFR0_BITPERM 0x1
+#define ID_AA64ZFR0_AES 0x1
+#define ID_AA64ZFR0_AES_PMULL 0x2
+#define ID_AA64ZFR0_SVEVER_SVE2 0x1
+
+/* id_aa64mmfr0 */
+#define ID_AA64MMFR0_ECV_SHIFT 60
+#define ID_AA64MMFR0_FGT_SHIFT 56
+#define ID_AA64MMFR0_EXS_SHIFT 44
+#define ID_AA64MMFR0_TGRAN4_2_SHIFT 40
+#define ID_AA64MMFR0_TGRAN64_2_SHIFT 36
+#define ID_AA64MMFR0_TGRAN16_2_SHIFT 32
+#define ID_AA64MMFR0_TGRAN4_SHIFT 28
+#define ID_AA64MMFR0_TGRAN64_SHIFT 24
+#define ID_AA64MMFR0_TGRAN16_SHIFT 20
+#define ID_AA64MMFR0_BIGENDEL0_SHIFT 16
+#define ID_AA64MMFR0_SNSMEM_SHIFT 12
+#define ID_AA64MMFR0_BIGENDEL_SHIFT 8
+#define ID_AA64MMFR0_ASID_SHIFT 4
+#define ID_AA64MMFR0_PARANGE_SHIFT 0
+
+#define ID_AA64MMFR0_ASID_8 0x0
+#define ID_AA64MMFR0_ASID_16 0x2
+
+#define ID_AA64MMFR0_TGRAN4_NI 0xf
+#define ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN 0x0
+#define ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX 0x7
+#define ID_AA64MMFR0_TGRAN64_NI 0xf
+#define ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN 0x0
+#define ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX 0x7
+#define ID_AA64MMFR0_TGRAN16_NI 0x0
+#define ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN 0x1
+#define ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX 0xf
+
+#define ID_AA64MMFR0_PARANGE_32 0x0
+#define ID_AA64MMFR0_PARANGE_36 0x1
+#define ID_AA64MMFR0_PARANGE_40 0x2
+#define ID_AA64MMFR0_PARANGE_42 0x3
+#define ID_AA64MMFR0_PARANGE_44 0x4
+#define ID_AA64MMFR0_PARANGE_48 0x5
+#define ID_AA64MMFR0_PARANGE_52 0x6
+
+#define ARM64_MIN_PARANGE_BITS 32
+
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_DEFAULT 0x0
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_NONE 0x1
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MIN 0x2
+#define ID_AA64MMFR0_TGRAN_2_SUPPORTED_MAX 0x7
+
+#ifdef CONFIG_ARM64_PA_BITS_52
+#define ID_AA64MMFR0_PARANGE_MAX ID_AA64MMFR0_PARANGE_52
+#else
+#define ID_AA64MMFR0_PARANGE_MAX ID_AA64MMFR0_PARANGE_48
+#endif
+
+/* id_aa64mmfr1 */
+#define ID_AA64MMFR1_ETS_SHIFT 36
+#define ID_AA64MMFR1_TWED_SHIFT 32
+#define ID_AA64MMFR1_XNX_SHIFT 28
+#define ID_AA64MMFR1_SPECSEI_SHIFT 24
+#define ID_AA64MMFR1_PAN_SHIFT 20
+#define ID_AA64MMFR1_LOR_SHIFT 16
+#define ID_AA64MMFR1_HPD_SHIFT 12
+#define ID_AA64MMFR1_VHE_SHIFT 8
+#define ID_AA64MMFR1_VMIDBITS_SHIFT 4
+#define ID_AA64MMFR1_HADBS_SHIFT 0
+
+#define ID_AA64MMFR1_VMIDBITS_8 0
+#define ID_AA64MMFR1_VMIDBITS_16 2
+
+/* id_aa64mmfr2 */
+#define ID_AA64MMFR2_E0PD_SHIFT 60
+#define ID_AA64MMFR2_EVT_SHIFT 56
+#define ID_AA64MMFR2_BBM_SHIFT 52
+#define ID_AA64MMFR2_TTL_SHIFT 48
+#define ID_AA64MMFR2_FWB_SHIFT 40
+#define ID_AA64MMFR2_IDS_SHIFT 36
+#define ID_AA64MMFR2_AT_SHIFT 32
+#define ID_AA64MMFR2_ST_SHIFT 28
+#define ID_AA64MMFR2_NV_SHIFT 24
+#define ID_AA64MMFR2_CCIDX_SHIFT 20
+#define ID_AA64MMFR2_LVA_SHIFT 16
+#define ID_AA64MMFR2_IESB_SHIFT 12
+#define ID_AA64MMFR2_LSM_SHIFT 8
+#define ID_AA64MMFR2_UAO_SHIFT 4
+#define ID_AA64MMFR2_CNP_SHIFT 0
+
+/* id_aa64dfr0 */
+#define ID_AA64DFR0_MTPMU_SHIFT 48
+#define ID_AA64DFR0_TRBE_SHIFT 44
+#define ID_AA64DFR0_TRACE_FILT_SHIFT 40
+#define ID_AA64DFR0_DOUBLELOCK_SHIFT 36
+#define ID_AA64DFR0_PMSVER_SHIFT 32
+#define ID_AA64DFR0_CTX_CMPS_SHIFT 28
+#define ID_AA64DFR0_WRPS_SHIFT 20
+#define ID_AA64DFR0_BRPS_SHIFT 12
+#define ID_AA64DFR0_PMUVER_SHIFT 8
+#define ID_AA64DFR0_TRACEVER_SHIFT 4
+#define ID_AA64DFR0_DEBUGVER_SHIFT 0
+
+#define ID_AA64DFR0_PMUVER_8_0 0x1
+#define ID_AA64DFR0_PMUVER_8_1 0x4
+#define ID_AA64DFR0_PMUVER_8_4 0x5
+#define ID_AA64DFR0_PMUVER_8_5 0x6
+#define ID_AA64DFR0_PMUVER_IMP_DEF 0xf
+
+#define ID_AA64DFR0_PMSVER_8_2 0x1
+#define ID_AA64DFR0_PMSVER_8_3 0x2
+
+#define ID_DFR0_PERFMON_SHIFT 24
+
+#define ID_DFR0_PERFMON_8_0 0x3
+#define ID_DFR0_PERFMON_8_1 0x4
+#define ID_DFR0_PERFMON_8_4 0x5
+#define ID_DFR0_PERFMON_8_5 0x6
+
+#define ID_ISAR4_SWP_FRAC_SHIFT 28
+#define ID_ISAR4_PSR_M_SHIFT 24
+#define ID_ISAR4_SYNCH_PRIM_FRAC_SHIFT 20
+#define ID_ISAR4_BARRIER_SHIFT 16
+#define ID_ISAR4_SMC_SHIFT 12
+#define ID_ISAR4_WRITEBACK_SHIFT 8
+#define ID_ISAR4_WITHSHIFTS_SHIFT 4
+#define ID_ISAR4_UNPRIV_SHIFT 0
+
+#define ID_DFR1_MTPMU_SHIFT 0
+
+#define ID_ISAR0_DIVIDE_SHIFT 24
+#define ID_ISAR0_DEBUG_SHIFT 20
+#define ID_ISAR0_COPROC_SHIFT 16
+#define ID_ISAR0_CMPBRANCH_SHIFT 12
+#define ID_ISAR0_BITFIELD_SHIFT 8
+#define ID_ISAR0_BITCOUNT_SHIFT 4
+#define ID_ISAR0_SWAP_SHIFT 0
+
+#define ID_ISAR5_RDM_SHIFT 24
+#define ID_ISAR5_CRC32_SHIFT 16
+#define ID_ISAR5_SHA2_SHIFT 12
+#define ID_ISAR5_SHA1_SHIFT 8
+#define ID_ISAR5_AES_SHIFT 4
+#define ID_ISAR5_SEVL_SHIFT 0
+
+#define ID_ISAR6_I8MM_SHIFT 24
+#define ID_ISAR6_BF16_SHIFT 20
+#define ID_ISAR6_SPECRES_SHIFT 16
+#define ID_ISAR6_SB_SHIFT 12
+#define ID_ISAR6_FHM_SHIFT 8
+#define ID_ISAR6_DP_SHIFT 4
+#define ID_ISAR6_JSCVT_SHIFT 0
+
+#define ID_MMFR0_INNERSHR_SHIFT 28
+#define ID_MMFR0_FCSE_SHIFT 24
+#define ID_MMFR0_AUXREG_SHIFT 20
+#define ID_MMFR0_TCM_SHIFT 16
+#define ID_MMFR0_SHARELVL_SHIFT 12
+#define ID_MMFR0_OUTERSHR_SHIFT 8
+#define ID_MMFR0_PMSA_SHIFT 4
+#define ID_MMFR0_VMSA_SHIFT 0
+
+#define ID_MMFR4_EVT_SHIFT 28
+#define ID_MMFR4_CCIDX_SHIFT 24
+#define ID_MMFR4_LSM_SHIFT 20
+#define ID_MMFR4_HPDS_SHIFT 16
+#define ID_MMFR4_CNP_SHIFT 12
+#define ID_MMFR4_XNX_SHIFT 8
+#define ID_MMFR4_AC2_SHIFT 4
+#define ID_MMFR4_SPECSEI_SHIFT 0
+
+#define ID_MMFR5_ETS_SHIFT 0
+
+#define ID_PFR0_DIT_SHIFT 24
+#define ID_PFR0_CSV2_SHIFT 16
+#define ID_PFR0_STATE3_SHIFT 12
+#define ID_PFR0_STATE2_SHIFT 8
+#define ID_PFR0_STATE1_SHIFT 4
+#define ID_PFR0_STATE0_SHIFT 0
+
+#define ID_DFR0_PERFMON_SHIFT 24
+#define ID_DFR0_MPROFDBG_SHIFT 20
+#define ID_DFR0_MMAPTRC_SHIFT 16
+#define ID_DFR0_COPTRC_SHIFT 12
+#define ID_DFR0_MMAPDBG_SHIFT 8
+#define ID_DFR0_COPSDBG_SHIFT 4
+#define ID_DFR0_COPDBG_SHIFT 0
+
+#define ID_PFR2_SSBS_SHIFT 4
+#define ID_PFR2_CSV3_SHIFT 0
+
+#define MVFR0_FPROUND_SHIFT 28
+#define MVFR0_FPSHVEC_SHIFT 24
+#define MVFR0_FPSQRT_SHIFT 20
+#define MVFR0_FPDIVIDE_SHIFT 16
+#define MVFR0_FPTRAP_SHIFT 12
+#define MVFR0_FPDP_SHIFT 8
+#define MVFR0_FPSP_SHIFT 4
+#define MVFR0_SIMD_SHIFT 0
+
+#define MVFR1_SIMDFMAC_SHIFT 28
+#define MVFR1_FPHP_SHIFT 24
+#define MVFR1_SIMDHP_SHIFT 20
+#define MVFR1_SIMDSP_SHIFT 16
+#define MVFR1_SIMDINT_SHIFT 12
+#define MVFR1_SIMDLS_SHIFT 8
+#define MVFR1_FPDNAN_SHIFT 4
+#define MVFR1_FPFTZ_SHIFT 0
+
+#define ID_PFR1_GIC_SHIFT 28
+#define ID_PFR1_VIRT_FRAC_SHIFT 24
+#define ID_PFR1_SEC_FRAC_SHIFT 20
+#define ID_PFR1_GENTIMER_SHIFT 16
+#define ID_PFR1_VIRTUALIZATION_SHIFT 12
+#define ID_PFR1_MPROGMOD_SHIFT 8
+#define ID_PFR1_SECURITY_SHIFT 4
+#define ID_PFR1_PROGMOD_SHIFT 0
+
+#if defined(CONFIG_ARM64_4K_PAGES)
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN4_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN4_SUPPORTED_MIN
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN4_SUPPORTED_MAX
+#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN4_2_SHIFT
+#elif defined(CONFIG_ARM64_16K_PAGES)
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN16_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN16_SUPPORTED_MIN
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN16_SUPPORTED_MAX
+#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN16_2_SHIFT
+#elif defined(CONFIG_ARM64_64K_PAGES)
+#define ID_AA64MMFR0_TGRAN_SHIFT ID_AA64MMFR0_TGRAN64_SHIFT
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MIN ID_AA64MMFR0_TGRAN64_SUPPORTED_MIN
+#define ID_AA64MMFR0_TGRAN_SUPPORTED_MAX ID_AA64MMFR0_TGRAN64_SUPPORTED_MAX
+#define ID_AA64MMFR0_TGRAN_2_SHIFT ID_AA64MMFR0_TGRAN64_2_SHIFT
+#endif
+
+#define MVFR2_FPMISC_SHIFT 4
+#define MVFR2_SIMDMISC_SHIFT 0
+
+#define DCZID_DZP_SHIFT 4
+#define DCZID_BS_SHIFT 0
+
+/*
+ * The ZCR_ELx_LEN_* definitions intentionally include bits [8:4] which
+ * are reserved by the SVE architecture for future expansion of the LEN
+ * field, with compatible semantics.
+ */
+#define ZCR_ELx_LEN_SHIFT 0
+#define ZCR_ELx_LEN_SIZE 9
+#define ZCR_ELx_LEN_MASK 0x1ff
+
+#define CPACR_EL1_ZEN_EL1EN (BIT(16)) /* enable EL1 access */
+#define CPACR_EL1_ZEN_EL0EN (BIT(17)) /* enable EL0 access, if EL1EN set */
+#define CPACR_EL1_ZEN (CPACR_EL1_ZEN_EL1EN | CPACR_EL1_ZEN_EL0EN)
+
+/* TCR EL1 Bit Definitions */
+#define SYS_TCR_EL1_TCMA1 (BIT(58))
+#define SYS_TCR_EL1_TCMA0 (BIT(57))
+
+/* GCR_EL1 Definitions */
+#define SYS_GCR_EL1_RRND (BIT(16))
+#define SYS_GCR_EL1_EXCL_MASK 0xffffUL
+
+/* RGSR_EL1 Definitions */
+#define SYS_RGSR_EL1_TAG_MASK 0xfUL
+#define SYS_RGSR_EL1_SEED_SHIFT 8
+#define SYS_RGSR_EL1_SEED_MASK 0xffffUL
+
+/* GMID_EL1 field definitions */
+#define SYS_GMID_EL1_BS_SHIFT 0
+#define SYS_GMID_EL1_BS_SIZE 4
+
+/* TFSR{,E0}_EL1 bit definitions */
+#define SYS_TFSR_EL1_TF0_SHIFT 0
+#define SYS_TFSR_EL1_TF1_SHIFT 1
+#define SYS_TFSR_EL1_TF0 (UL(1) << SYS_TFSR_EL1_TF0_SHIFT)
+#define SYS_TFSR_EL1_TF1 (UL(1) << SYS_TFSR_EL1_TF1_SHIFT)
+
+/* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */
+#define SYS_MPIDR_SAFE_VAL (BIT(31))
+
+#define TRFCR_ELx_TS_SHIFT 5
+#define TRFCR_ELx_TS_VIRTUAL ((0x1UL) << TRFCR_ELx_TS_SHIFT)
+#define TRFCR_ELx_TS_GUEST_PHYSICAL ((0x2UL) << TRFCR_ELx_TS_SHIFT)
+#define TRFCR_ELx_TS_PHYSICAL ((0x3UL) << TRFCR_ELx_TS_SHIFT)
+#define TRFCR_EL2_CX BIT(3)
+#define TRFCR_ELx_ExTRE BIT(1)
+#define TRFCR_ELx_E0TRE BIT(0)
+
+
+/* GIC Hypervisor interface registers */
+/* ICH_MISR_EL2 bit definitions */
+#define ICH_MISR_EOI (1 << 0)
+#define ICH_MISR_U (1 << 1)
+
+/* ICH_LR*_EL2 bit definitions */
+#define ICH_LR_VIRTUAL_ID_MASK ((1ULL << 32) - 1)
+
+#define ICH_LR_EOI (1ULL << 41)
+#define ICH_LR_GROUP (1ULL << 60)
+#define ICH_LR_HW (1ULL << 61)
+#define ICH_LR_STATE (3ULL << 62)
+#define ICH_LR_PENDING_BIT (1ULL << 62)
+#define ICH_LR_ACTIVE_BIT (1ULL << 63)
+#define ICH_LR_PHYS_ID_SHIFT 32
+#define ICH_LR_PHYS_ID_MASK (0x3ffULL << ICH_LR_PHYS_ID_SHIFT)
+#define ICH_LR_PRIORITY_SHIFT 48
+#define ICH_LR_PRIORITY_MASK (0xffULL << ICH_LR_PRIORITY_SHIFT)
+
+/* ICH_HCR_EL2 bit definitions */
+#define ICH_HCR_EN (1 << 0)
+#define ICH_HCR_UIE (1 << 1)
+#define ICH_HCR_NPIE (1 << 3)
+#define ICH_HCR_TC (1 << 10)
+#define ICH_HCR_TALL0 (1 << 11)
+#define ICH_HCR_TALL1 (1 << 12)
+#define ICH_HCR_EOIcount_SHIFT 27
+#define ICH_HCR_EOIcount_MASK (0x1f << ICH_HCR_EOIcount_SHIFT)
+
+/* ICH_VMCR_EL2 bit definitions */
+#define ICH_VMCR_ACK_CTL_SHIFT 2
+#define ICH_VMCR_ACK_CTL_MASK (1 << ICH_VMCR_ACK_CTL_SHIFT)
+#define ICH_VMCR_FIQ_EN_SHIFT 3
+#define ICH_VMCR_FIQ_EN_MASK (1 << ICH_VMCR_FIQ_EN_SHIFT)
+#define ICH_VMCR_CBPR_SHIFT 4
+#define ICH_VMCR_CBPR_MASK (1 << ICH_VMCR_CBPR_SHIFT)
+#define ICH_VMCR_EOIM_SHIFT 9
+#define ICH_VMCR_EOIM_MASK (1 << ICH_VMCR_EOIM_SHIFT)
+#define ICH_VMCR_BPR1_SHIFT 18
+#define ICH_VMCR_BPR1_MASK (7 << ICH_VMCR_BPR1_SHIFT)
+#define ICH_VMCR_BPR0_SHIFT 21
+#define ICH_VMCR_BPR0_MASK (7 << ICH_VMCR_BPR0_SHIFT)
+#define ICH_VMCR_PMR_SHIFT 24
+#define ICH_VMCR_PMR_MASK (0xffUL << ICH_VMCR_PMR_SHIFT)
+#define ICH_VMCR_ENG0_SHIFT 0
+#define ICH_VMCR_ENG0_MASK (1 << ICH_VMCR_ENG0_SHIFT)
+#define ICH_VMCR_ENG1_SHIFT 1
+#define ICH_VMCR_ENG1_MASK (1 << ICH_VMCR_ENG1_SHIFT)
+
+/* ICH_VTR_EL2 bit definitions */
+#define ICH_VTR_PRI_BITS_SHIFT 29
+#define ICH_VTR_PRI_BITS_MASK (7 << ICH_VTR_PRI_BITS_SHIFT)
+#define ICH_VTR_ID_BITS_SHIFT 23
+#define ICH_VTR_ID_BITS_MASK (7 << ICH_VTR_ID_BITS_SHIFT)
+#define ICH_VTR_SEIS_SHIFT 22
+#define ICH_VTR_SEIS_MASK (1 << ICH_VTR_SEIS_SHIFT)
+#define ICH_VTR_A3V_SHIFT 21
+#define ICH_VTR_A3V_MASK (1 << ICH_VTR_A3V_SHIFT)
+
+#define ARM64_FEATURE_FIELD_BITS 4
+
+/* Create a mask for the feature bits of the specified feature. */
+#define ARM64_FEATURE_MASK(x) (GENMASK_ULL(x##_SHIFT + ARM64_FEATURE_FIELD_BITS - 1, x##_SHIFT))
+
+#ifdef __ASSEMBLY__
+
+ .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30
+ .equ .L__reg_num_x\num, \num
+ .endr
+ .equ .L__reg_num_xzr, 31
+
+ .macro mrs_s, rt, sreg
+ __emit_inst(0xd5200000|(\sreg)|(.L__reg_num_\rt))
+ .endm
+
+ .macro msr_s, sreg, rt
+ __emit_inst(0xd5000000|(\sreg)|(.L__reg_num_\rt))
+ .endm
+
+#else
+
+#include <linux/build_bug.h>
+#include <linux/types.h>
+#include <asm/alternative.h>
+
+#define __DEFINE_MRS_MSR_S_REGNUM \
+" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30\n" \
+" .equ .L__reg_num_x\\num, \\num\n" \
+" .endr\n" \
+" .equ .L__reg_num_xzr, 31\n"
+
+#define DEFINE_MRS_S \
+ __DEFINE_MRS_MSR_S_REGNUM \
+" .macro mrs_s, rt, sreg\n" \
+ __emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt)) \
+" .endm\n"
+
+#define DEFINE_MSR_S \
+ __DEFINE_MRS_MSR_S_REGNUM \
+" .macro msr_s, sreg, rt\n" \
+ __emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt)) \
+" .endm\n"
+
+#define UNDEFINE_MRS_S \
+" .purgem mrs_s\n"
+
+#define UNDEFINE_MSR_S \
+" .purgem msr_s\n"
+
+#define __mrs_s(v, r) \
+ DEFINE_MRS_S \
+" mrs_s " v ", " __stringify(r) "\n" \
+ UNDEFINE_MRS_S
+
+#define __msr_s(r, v) \
+ DEFINE_MSR_S \
+" msr_s " __stringify(r) ", " v "\n" \
+ UNDEFINE_MSR_S
+
+/*
+ * Unlike read_cpuid, calls to read_sysreg are never expected to be
+ * optimized away or replaced with synthetic values.
+ */
+#define read_sysreg(r) ({ \
+ u64 __val; \
+ asm volatile("mrs %0, " __stringify(r) : "=r" (__val)); \
+ __val; \
+})
+
+/*
+ * The "Z" constraint normally means a zero immediate, but when combined with
+ * the "%x0" template means XZR.
+ */
+#define write_sysreg(v, r) do { \
+ u64 __val = (u64)(v); \
+ asm volatile("msr " __stringify(r) ", %x0" \
+ : : "rZ" (__val)); \
+} while (0)
+
+/*
+ * For registers without architectural names, or simply unsupported by
+ * GAS.
+ */
+#define read_sysreg_s(r) ({ \
+ u64 __val; \
+ asm volatile(__mrs_s("%0", r) : "=r" (__val)); \
+ __val; \
+})
+
+#define write_sysreg_s(v, r) do { \
+ u64 __val = (u64)(v); \
+ asm volatile(__msr_s(r, "%x0") : : "rZ" (__val)); \
+} while (0)
+
+/*
+ * Modify bits in a sysreg. Bits in the clear mask are zeroed, then bits in the
+ * set mask are set. Other bits are left as-is.
+ */
+#define sysreg_clear_set(sysreg, clear, set) do { \
+ u64 __scs_val = read_sysreg(sysreg); \
+ u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set); \
+ if (__scs_new != __scs_val) \
+ write_sysreg(__scs_new, sysreg); \
+} while (0)
+
+#define sysreg_clear_set_s(sysreg, clear, set) do { \
+ u64 __scs_val = read_sysreg_s(sysreg); \
+ u64 __scs_new = (__scs_val & ~(u64)(clear)) | (set); \
+ if (__scs_new != __scs_val) \
+ write_sysreg_s(__scs_new, sysreg); \
+} while (0)
+
+#define read_sysreg_par() ({ \
+ u64 par; \
+ asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412)); \
+ par = read_sysreg(par_el1); \
+ asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412)); \
+ par; \
+})
+
+#endif
+
+#endif /* __ASM_SYSREG_H */
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index b8dbabe24ac2..02444fc69bae 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -1,4 +1,5 @@
# SPDX-License-Identifier: GPL-2.0-only
+/aarch64/arch_timer
/aarch64/debug-exceptions
/aarch64/get-reg-list
/aarch64/psci_cpu_on_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index e6fba18d0b2c..36ccd2925c8f 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -35,7 +35,7 @@ endif
LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/rbtree.c lib/sparsebit.c lib/test_util.c lib/guest_modes.c lib/perf_test_util.c
LIBKVM_x86_64 = lib/x86_64/apic.c lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
-LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S
+LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c lib/aarch64/handlers.S lib/aarch64/spinlock.c lib/aarch64/gic.c lib/aarch64/gic_v3.c lib/aarch64/vgic.c
LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c lib/s390x/diag318_test_handler.c
TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
@@ -86,6 +86,7 @@ TEST_GEN_PROGS_x86_64 += set_memory_region_test
TEST_GEN_PROGS_x86_64 += steal_time
TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test
+TEST_GEN_PROGS_aarch64 += aarch64/arch_timer
TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
new file mode 100644
index 000000000000..bf6a45b0b8dc
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -0,0 +1,479 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * arch_timer.c - Tests the aarch64 timer IRQ functionality
+ *
+ * The test validates both the virtual and physical timer IRQs using
+ * CVAL and TVAL registers. This consitutes the four stages in the test.
+ * The guest's main thread configures the timer interrupt for a stage
+ * and waits for it to fire, with a timeout equal to the timer period.
+ * It asserts that the timeout doesn't exceed the timer period.
+ *
+ * On the other hand, upon receipt of an interrupt, the guest's interrupt
+ * handler validates the interrupt by checking if the architectural state
+ * is in compliance with the specifications.
+ *
+ * The test provides command-line options to configure the timer's
+ * period (-p), number of vCPUs (-n), and iterations per stage (-i).
+ * To stress-test the timer stack even more, an option to migrate the
+ * vCPUs across pCPUs (-m), at a particular rate, is also provided.
+ *
+ * Copyright (c) 2021, Google LLC.
+ */
+
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <pthread.h>
+#include <linux/kvm.h>
+#include <linux/sizes.h>
+#include <linux/bitmap.h>
+#include <sys/sysinfo.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "delay.h"
+#include "arch_timer.h"
+#include "gic.h"
+#include "vgic.h"
+
+#define NR_VCPUS_DEF 4
+#define NR_TEST_ITERS_DEF 5
+#define TIMER_TEST_PERIOD_MS_DEF 10
+#define TIMER_TEST_ERR_MARGIN_US 100
+#define TIMER_TEST_MIGRATION_FREQ_MS 2
+
+struct test_args {
+ int nr_vcpus;
+ int nr_iter;
+ int timer_period_ms;
+ int migration_freq_ms;
+};
+
+static struct test_args test_args = {
+ .nr_vcpus = NR_VCPUS_DEF,
+ .nr_iter = NR_TEST_ITERS_DEF,
+ .timer_period_ms = TIMER_TEST_PERIOD_MS_DEF,
+ .migration_freq_ms = TIMER_TEST_MIGRATION_FREQ_MS,
+};
+
+#define msecs_to_usecs(msec) ((msec) * 1000LL)
+
+#define GICD_BASE_GPA 0x8000000ULL
+#define GICR_BASE_GPA 0x80A0000ULL
+
+enum guest_stage {
+ GUEST_STAGE_VTIMER_CVAL = 1,
+ GUEST_STAGE_VTIMER_TVAL,
+ GUEST_STAGE_PTIMER_CVAL,
+ GUEST_STAGE_PTIMER_TVAL,
+ GUEST_STAGE_MAX,
+};
+
+/* Shared variables between host and guest */
+struct test_vcpu_shared_data {
+ int nr_iter;
+ enum guest_stage guest_stage;
+ uint64_t xcnt;
+};
+
+struct test_vcpu {
+ uint32_t vcpuid;
+ pthread_t pt_vcpu_run;
+ struct kvm_vm *vm;
+};
+
+static struct test_vcpu test_vcpu[KVM_MAX_VCPUS];
+static struct test_vcpu_shared_data vcpu_shared_data[KVM_MAX_VCPUS];
+
+static int vtimer_irq, ptimer_irq;
+
+static unsigned long *vcpu_done_map;
+static pthread_mutex_t vcpu_done_map_lock;
+
+static void
+guest_configure_timer_action(struct test_vcpu_shared_data *shared_data)
+{
+ switch (shared_data->guest_stage) {
+ case GUEST_STAGE_VTIMER_CVAL:
+ timer_set_next_cval_ms(VIRTUAL, test_args.timer_period_ms);
+ shared_data->xcnt = timer_get_cntct(VIRTUAL);
+ timer_set_ctl(VIRTUAL, CTL_ENABLE);
+ break;
+ case GUEST_STAGE_VTIMER_TVAL:
+ timer_set_next_tval_ms(VIRTUAL, test_args.timer_period_ms);
+ shared_data->xcnt = timer_get_cntct(VIRTUAL);
+ timer_set_ctl(VIRTUAL, CTL_ENABLE);
+ break;
+ case GUEST_STAGE_PTIMER_CVAL:
+ timer_set_next_cval_ms(PHYSICAL, test_args.timer_period_ms);
+ shared_data->xcnt = timer_get_cntct(PHYSICAL);
+ timer_set_ctl(PHYSICAL, CTL_ENABLE);
+ break;
+ case GUEST_STAGE_PTIMER_TVAL:
+ timer_set_next_tval_ms(PHYSICAL, test_args.timer_period_ms);
+ shared_data->xcnt = timer_get_cntct(PHYSICAL);
+ timer_set_ctl(PHYSICAL, CTL_ENABLE);
+ break;
+ default:
+ GUEST_ASSERT(0);
+ }
+}
+
+static void guest_validate_irq(unsigned int intid,
+ struct test_vcpu_shared_data *shared_data)
+{
+ enum guest_stage stage = shared_data->guest_stage;
+ uint64_t xcnt = 0, xcnt_diff_us, cval = 0;
+ unsigned long xctl = 0;
+ unsigned int timer_irq = 0;
+
+ if (stage == GUEST_STAGE_VTIMER_CVAL ||
+ stage == GUEST_STAGE_VTIMER_TVAL) {
+ xctl = timer_get_ctl(VIRTUAL);
+ timer_set_ctl(VIRTUAL, CTL_IMASK);
+ xcnt = timer_get_cntct(VIRTUAL);
+ cval = timer_get_cval(VIRTUAL);
+ timer_irq = vtimer_irq;
+ } else if (stage == GUEST_STAGE_PTIMER_CVAL ||
+ stage == GUEST_STAGE_PTIMER_TVAL) {
+ xctl = timer_get_ctl(PHYSICAL);
+ timer_set_ctl(PHYSICAL, CTL_IMASK);
+ xcnt = timer_get_cntct(PHYSICAL);
+ cval = timer_get_cval(PHYSICAL);
+ timer_irq = ptimer_irq;
+ } else {
+ GUEST_ASSERT(0);
+ }
+
+ xcnt_diff_us = cycles_to_usec(xcnt - shared_data->xcnt);
+
+ /* Make sure we are dealing with the correct timer IRQ */
+ GUEST_ASSERT_2(intid == timer_irq, intid, timer_irq);
+
+ /* Basic 'timer condition met' check */
+ GUEST_ASSERT_3(xcnt >= cval, xcnt, cval, xcnt_diff_us);
+ GUEST_ASSERT_1(xctl & CTL_ISTATUS, xctl);
+}
+
+static void guest_irq_handler(struct ex_regs *regs)
+{
+ unsigned int intid = gic_get_and_ack_irq();
+ uint32_t cpu = guest_get_vcpuid();
+ struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu];
+
+ guest_validate_irq(intid, shared_data);
+
+ WRITE_ONCE(shared_data->nr_iter, shared_data->nr_iter + 1);
+
+ gic_set_eoi(intid);
+}
+
+static void guest_run_stage(struct test_vcpu_shared_data *shared_data,
+ enum guest_stage stage)
+{
+ uint32_t irq_iter, config_iter;
+
+ shared_data->guest_stage = stage;
+ shared_data->nr_iter = 0;
+
+ for (config_iter = 0; config_iter < test_args.nr_iter; config_iter++) {
+ /* Setup the next interrupt */
+ guest_configure_timer_action(shared_data);
+
+ /* Setup a timeout for the interrupt to arrive */
+ udelay(msecs_to_usecs(test_args.timer_period_ms) +
+ TIMER_TEST_ERR_MARGIN_US);
+
+ irq_iter = READ_ONCE(shared_data->nr_iter);
+ GUEST_ASSERT_2(config_iter + 1 == irq_iter,
+ config_iter + 1, irq_iter);
+ }
+}
+
+static void guest_code(void)
+{
+ uint32_t cpu = guest_get_vcpuid();
+ struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[cpu];
+
+ local_irq_disable();
+
+ gic_init(GIC_V3, test_args.nr_vcpus,
+ (void *)GICD_BASE_GPA, (void *)GICR_BASE_GPA);
+
+ timer_set_ctl(VIRTUAL, CTL_IMASK);
+ timer_set_ctl(PHYSICAL, CTL_IMASK);
+
+ gic_irq_enable(vtimer_irq);
+ gic_irq_enable(ptimer_irq);
+ local_irq_enable();
+
+ guest_run_stage(shared_data, GUEST_STAGE_VTIMER_CVAL);
+ guest_run_stage(shared_data, GUEST_STAGE_VTIMER_TVAL);
+ guest_run_stage(shared_data, GUEST_STAGE_PTIMER_CVAL);
+ guest_run_stage(shared_data, GUEST_STAGE_PTIMER_TVAL);
+
+ GUEST_DONE();
+}
+
+static void *test_vcpu_run(void *arg)
+{
+ struct ucall uc;
+ struct test_vcpu *vcpu = arg;
+ struct kvm_vm *vm = vcpu->vm;
+ uint32_t vcpuid = vcpu->vcpuid;
+ struct test_vcpu_shared_data *shared_data = &vcpu_shared_data[vcpuid];
+
+ vcpu_run(vm, vcpuid);
+
+ /* Currently, any exit from guest is an indication of completion */
+ pthread_mutex_lock(&vcpu_done_map_lock);
+ set_bit(vcpuid, vcpu_done_map);
+ pthread_mutex_unlock(&vcpu_done_map_lock);
+
+ switch (get_ucall(vm, vcpuid, &uc)) {
+ case UCALL_SYNC:
+ case UCALL_DONE:
+ break;
+ case UCALL_ABORT:
+ sync_global_from_guest(vm, *shared_data);
+ TEST_FAIL("%s at %s:%ld\n\tvalues: %lu, %lu; %lu, vcpu: %u; stage: %u; iter: %u",
+ (const char *)uc.args[0], __FILE__, uc.args[1],
+ uc.args[2], uc.args[3], uc.args[4], vcpuid,
+ shared_data->guest_stage, shared_data->nr_iter);
+ break;
+ default:
+ TEST_FAIL("Unexpected guest exit\n");
+ }
+
+ return NULL;
+}
+
+static uint32_t test_get_pcpu(void)
+{
+ uint32_t pcpu;
+ unsigned int nproc_conf;
+ cpu_set_t online_cpuset;
+
+ nproc_conf = get_nprocs_conf();
+ sched_getaffinity(0, sizeof(cpu_set_t), &online_cpuset);
+
+ /* Randomly find an available pCPU to place a vCPU on */
+ do {
+ pcpu = rand() % nproc_conf;
+ } while (!CPU_ISSET(pcpu, &online_cpuset));
+
+ return pcpu;
+}
+
+static int test_migrate_vcpu(struct test_vcpu *vcpu)
+{
+ int ret;
+ cpu_set_t cpuset;
+ uint32_t new_pcpu = test_get_pcpu();
+
+ CPU_ZERO(&cpuset);
+ CPU_SET(new_pcpu, &cpuset);
+
+ pr_debug("Migrating vCPU: %u to pCPU: %u\n", vcpu->vcpuid, new_pcpu);
+
+ ret = pthread_setaffinity_np(vcpu->pt_vcpu_run,
+ sizeof(cpuset), &cpuset);
+
+ /* Allow the error where the vCPU thread is already finished */
+ TEST_ASSERT(ret == 0 || ret == ESRCH,
+ "Failed to migrate the vCPU:%u to pCPU: %u; ret: %d\n",
+ vcpu->vcpuid, new_pcpu, ret);
+
+ return ret;
+}
+
+static void *test_vcpu_migration(void *arg)
+{
+ unsigned int i, n_done;
+ bool vcpu_done;
+
+ do {
+ usleep(msecs_to_usecs(test_args.migration_freq_ms));
+
+ for (n_done = 0, i = 0; i < test_args.nr_vcpus; i++) {
+ pthread_mutex_lock(&vcpu_done_map_lock);
+ vcpu_done = test_bit(i, vcpu_done_map);
+ pthread_mutex_unlock(&vcpu_done_map_lock);
+
+ if (vcpu_done) {
+ n_done++;
+ continue;
+ }
+
+ test_migrate_vcpu(&test_vcpu[i]);
+ }
+ } while (test_args.nr_vcpus != n_done);
+
+ return NULL;
+}
+
+static void test_run(struct kvm_vm *vm)
+{
+ int i, ret;
+ pthread_t pt_vcpu_migration;
+
+ pthread_mutex_init(&vcpu_done_map_lock, NULL);
+ vcpu_done_map = bitmap_zalloc(test_args.nr_vcpus);
+ TEST_ASSERT(vcpu_done_map, "Failed to allocate vcpu done bitmap\n");
+
+ for (i = 0; i < test_args.nr_vcpus; i++) {
+ ret = pthread_create(&test_vcpu[i].pt_vcpu_run, NULL,
+ test_vcpu_run, &test_vcpu[i]);
+ TEST_ASSERT(!ret, "Failed to create vCPU-%d pthread\n", i);
+ }
+
+ /* Spawn a thread to control the vCPU migrations */
+ if (test_args.migration_freq_ms) {
+ srand(time(NULL));
+
+ ret = pthread_create(&pt_vcpu_migration, NULL,
+ test_vcpu_migration, NULL);
+ TEST_ASSERT(!ret, "Failed to create the migration pthread\n");
+ }
+
+
+ for (i = 0; i < test_args.nr_vcpus; i++)
+ pthread_join(test_vcpu[i].pt_vcpu_run, NULL);
+
+ if (test_args.migration_freq_ms)
+ pthread_join(pt_vcpu_migration, NULL);
+
+ bitmap_free(vcpu_done_map);
+}
+
+static void test_init_timer_irq(struct kvm_vm *vm)
+{
+ /* Timer initid should be same for all the vCPUs, so query only vCPU-0 */
+ int vcpu0_fd = vcpu_get_fd(vm, 0);
+
+ kvm_device_access(vcpu0_fd, KVM_ARM_VCPU_TIMER_CTRL,
+ KVM_ARM_VCPU_TIMER_IRQ_PTIMER, &ptimer_irq, false);
+ kvm_device_access(vcpu0_fd, KVM_ARM_VCPU_TIMER_CTRL,
+ KVM_ARM_VCPU_TIMER_IRQ_VTIMER, &vtimer_irq, false);
+
+ sync_global_to_guest(vm, ptimer_irq);
+ sync_global_to_guest(vm, vtimer_irq);
+
+ pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq);
+}
+
+static struct kvm_vm *test_vm_create(void)
+{
+ struct kvm_vm *vm;
+ unsigned int i;
+ int nr_vcpus = test_args.nr_vcpus;
+
+ vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
+
+ vm_init_descriptor_tables(vm);
+ vm_install_exception_handler(vm, VECTOR_IRQ_CURRENT, guest_irq_handler);
+
+ for (i = 0; i < nr_vcpus; i++) {
+ vcpu_init_descriptor_tables(vm, i);
+
+ test_vcpu[i].vcpuid = i;
+ test_vcpu[i].vm = vm;
+ }
+
+ ucall_init(vm, NULL);
+ test_init_timer_irq(vm);
+ vgic_v3_setup(vm, nr_vcpus, GICD_BASE_GPA, GICR_BASE_GPA);
+
+ /* Make all the test's cmdline args visible to the guest */
+ sync_global_to_guest(vm, test_args);
+
+ return vm;
+}
+
+static void test_print_help(char *name)
+{
+ pr_info("Usage: %s [-h] [-n nr_vcpus] [-i iterations] [-p timer_period_ms]\n",
+ name);
+ pr_info("\t-n: Number of vCPUs to configure (default: %u; max: %u)\n",
+ NR_VCPUS_DEF, KVM_MAX_VCPUS);
+ pr_info("\t-i: Number of iterations per stage (default: %u)\n",
+ NR_TEST_ITERS_DEF);
+ pr_info("\t-p: Periodicity (in ms) of the guest timer (default: %u)\n",
+ TIMER_TEST_PERIOD_MS_DEF);
+ pr_info("\t-m: Frequency (in ms) of vCPUs to migrate to different pCPU. 0 to turn off (default: %u)\n",
+ TIMER_TEST_MIGRATION_FREQ_MS);
+ pr_info("\t-h: print this help screen\n");
+}
+
+static bool parse_args(int argc, char *argv[])
+{
+ int opt;
+
+ while ((opt = getopt(argc, argv, "hn:i:p:m:")) != -1) {
+ switch (opt) {
+ case 'n':
+ test_args.nr_vcpus = atoi(optarg);
+ if (test_args.nr_vcpus <= 0) {
+ pr_info("Positive value needed for -n\n");
+ goto err;
+ } else if (test_args.nr_vcpus > KVM_MAX_VCPUS) {
+ pr_info("Max allowed vCPUs: %u\n",
+ KVM_MAX_VCPUS);
+ goto err;
+ }
+ break;
+ case 'i':
+ test_args.nr_iter = atoi(optarg);
+ if (test_args.nr_iter <= 0) {
+ pr_info("Positive value needed for -i\n");
+ goto err;
+ }
+ break;
+ case 'p':
+ test_args.timer_period_ms = atoi(optarg);
+ if (test_args.timer_period_ms <= 0) {
+ pr_info("Positive value needed for -p\n");
+ goto err;
+ }
+ break;
+ case 'm':
+ test_args.migration_freq_ms = atoi(optarg);
+ if (test_args.migration_freq_ms < 0) {
+ pr_info("0 or positive value needed for -m\n");
+ goto err;
+ }
+ break;
+ case 'h':
+ default:
+ goto err;
+ }
+ }
+
+ return true;
+
+err:
+ test_print_help(argv[0]);
+ return false;
+}
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vm *vm;
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ if (!parse_args(argc, argv))
+ exit(KSFT_SKIP);
+
+ if (test_args.migration_freq_ms && get_nprocs() < 2) {
+ print_skip("At least two physical CPUs needed for vCPU migration");
+ exit(KSFT_SKIP);
+ }
+
+ vm = test_vm_create();
+ test_run(vm);
+ kvm_vm_free(vm);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
index e5e6c92b60da..ea189d83abf7 100644
--- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
+++ b/tools/testing/selftests/kvm/aarch64/debug-exceptions.c
@@ -34,16 +34,16 @@ static void reset_debug_state(void)
{
asm volatile("msr daifset, #8");
- write_sysreg(osdlr_el1, 0);
- write_sysreg(oslar_el1, 0);
+ write_sysreg(0, osdlr_el1);
+ write_sysreg(0, oslar_el1);
isb();
- write_sysreg(mdscr_el1, 0);
+ write_sysreg(0, mdscr_el1);
/* This test only uses the first bp and wp slot. */
- write_sysreg(dbgbvr0_el1, 0);
- write_sysreg(dbgbcr0_el1, 0);
- write_sysreg(dbgwcr0_el1, 0);
- write_sysreg(dbgwvr0_el1, 0);
+ write_sysreg(0, dbgbvr0_el1);
+ write_sysreg(0, dbgbcr0_el1);
+ write_sysreg(0, dbgwcr0_el1);
+ write_sysreg(0, dbgwvr0_el1);
isb();
}
@@ -53,14 +53,14 @@ static void install_wp(uint64_t addr)
uint32_t mdscr;
wcr = DBGWCR_LEN8 | DBGWCR_RD | DBGWCR_WR | DBGWCR_EL1 | DBGWCR_E;
- write_sysreg(dbgwcr0_el1, wcr);
- write_sysreg(dbgwvr0_el1, addr);
+ write_sysreg(wcr, dbgwcr0_el1);
+ write_sysreg(addr, dbgwvr0_el1);
isb();
asm volatile("msr daifclr, #8");
mdscr = read_sysreg(mdscr_el1) | MDSCR_KDE | MDSCR_MDE;
- write_sysreg(mdscr_el1, mdscr);
+ write_sysreg(mdscr, mdscr_el1);
isb();
}
@@ -70,14 +70,14 @@ static void install_hw_bp(uint64_t addr)
uint32_t mdscr;
bcr = DBGBCR_LEN8 | DBGBCR_EXEC | DBGBCR_EL1 | DBGBCR_E;
- write_sysreg(dbgbcr0_el1, bcr);
- write_sysreg(dbgbvr0_el1, addr);
+ write_sysreg(bcr, dbgbcr0_el1);
+ write_sysreg(addr, dbgbvr0_el1);
isb();
asm volatile("msr daifclr, #8");
mdscr = read_sysreg(mdscr_el1) | MDSCR_KDE | MDSCR_MDE;
- write_sysreg(mdscr_el1, mdscr);
+ write_sysreg(mdscr, mdscr_el1);
isb();
}
@@ -88,7 +88,7 @@ static void install_ss(void)
asm volatile("msr daifclr, #8");
mdscr = read_sysreg(mdscr_el1) | MDSCR_KDE | MDSCR_SS;
- write_sysreg(mdscr_el1, mdscr);
+ write_sysreg(mdscr, mdscr_el1);
isb();
}
@@ -190,7 +190,7 @@ static int debug_version(struct kvm_vm *vm)
{
uint64_t id_aa64dfr0;
- get_reg(vm, VCPU_ID, ARM64_SYS_REG(ID_AA64DFR0_EL1), &id_aa64dfr0);
+ get_reg(vm, VCPU_ID, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &id_aa64dfr0);
return id_aa64dfr0 & 0xf;
}
diff --git a/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c
index 018c269990e1..4c5f6814030f 100644
--- a/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c
+++ b/tools/testing/selftests/kvm/aarch64/psci_cpu_on_test.c
@@ -91,7 +91,7 @@ int main(void)
init.features[0] |= (1 << KVM_ARM_VCPU_POWER_OFF);
aarch64_vcpu_add_default(vm, VCPU_ID_TARGET, &init, guest_main);
- get_reg(vm, VCPU_ID_TARGET, ARM64_SYS_REG(MPIDR_EL1), &target_mpidr);
+ get_reg(vm, VCPU_ID_TARGET, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr);
vcpu_args_set(vm, VCPU_ID_SOURCE, 1, target_mpidr & MPIDR_HWID_BITMASK);
vcpu_run(vm, VCPU_ID_SOURCE);
diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/aarch64/vgic_init.c
index 623f31a14326..34379c98d2f4 100644
--- a/tools/testing/selftests/kvm/aarch64/vgic_init.c
+++ b/tools/testing/selftests/kvm/aarch64/vgic_init.c
@@ -13,25 +13,28 @@
#include "test_util.h"
#include "kvm_util.h"
#include "processor.h"
+#include "vgic.h"
#define NR_VCPUS 4
-#define REDIST_REGION_ATTR_ADDR(count, base, flags, index) (((uint64_t)(count) << 52) | \
- ((uint64_t)((base) >> 16) << 16) | ((uint64_t)(flags) << 12) | index)
#define REG_OFFSET(vcpu, offset) (((uint64_t)vcpu << 32) | offset)
#define GICR_TYPER 0x8
+#define VGIC_DEV_IS_V2(_d) ((_d) == KVM_DEV_TYPE_ARM_VGIC_V2)
+#define VGIC_DEV_IS_V3(_d) ((_d) == KVM_DEV_TYPE_ARM_VGIC_V3)
+
struct vm_gic {
struct kvm_vm *vm;
int gic_fd;
+ uint32_t gic_dev_type;
};
-static int max_ipa_bits;
+static uint64_t max_phys_size;
/* helper to access a redistributor register */
-static int access_redist_reg(int gicv3_fd, int vcpu, int offset,
- uint32_t *val, bool write)
+static int access_v3_redist_reg(int gicv3_fd, int vcpu, int offset,
+ uint32_t *val, bool write)
{
uint64_t attr = REG_OFFSET(vcpu, offset);
@@ -58,12 +61,13 @@ static int run_vcpu(struct kvm_vm *vm, uint32_t vcpuid)
return 0;
}
-static struct vm_gic vm_gic_create(void)
+static struct vm_gic vm_gic_create_with_vcpus(uint32_t gic_dev_type, uint32_t nr_vcpus)
{
struct vm_gic v;
- v.vm = vm_create_default_with_vcpus(NR_VCPUS, 0, 0, guest_code, NULL);
- v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+ v.gic_dev_type = gic_dev_type;
+ v.vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
+ v.gic_fd = kvm_create_device(v.vm, gic_dev_type, false);
return v;
}
@@ -74,78 +78,129 @@ static void vm_gic_destroy(struct vm_gic *v)
kvm_vm_free(v->vm);
}
+struct vgic_region_attr {
+ uint64_t attr;
+ uint64_t size;
+ uint64_t alignment;
+};
+
+struct vgic_region_attr gic_v3_dist_region = {
+ .attr = KVM_VGIC_V3_ADDR_TYPE_DIST,
+ .size = 0x10000,
+ .alignment = 0x10000,
+};
+
+struct vgic_region_attr gic_v3_redist_region = {
+ .attr = KVM_VGIC_V3_ADDR_TYPE_REDIST,
+ .size = NR_VCPUS * 0x20000,
+ .alignment = 0x10000,
+};
+
+struct vgic_region_attr gic_v2_dist_region = {
+ .attr = KVM_VGIC_V2_ADDR_TYPE_DIST,
+ .size = 0x1000,
+ .alignment = 0x1000,
+};
+
+struct vgic_region_attr gic_v2_cpu_region = {
+ .attr = KVM_VGIC_V2_ADDR_TYPE_CPU,
+ .size = 0x2000,
+ .alignment = 0x1000,
+};
+
/**
- * Helper routine that performs KVM device tests in general and
- * especially ARM_VGIC_V3 ones. Eventually the ARM_VGIC_V3
- * device gets created, a legacy RDIST region is set at @0x0
- * and a DIST region is set @0x60000
+ * Helper routine that performs KVM device tests in general. Eventually the
+ * ARM_VGIC (GICv2 or GICv3) device gets created with an overlapping
+ * DIST/REDIST (or DIST/CPUIF for GICv2). Assumption is 4 vcpus are going to be
+ * used hence the overlap. In the case of GICv3, A RDIST region is set at @0x0
+ * and a DIST region is set @0x70000. The GICv2 case sets a CPUIF @0x0 and a
+ * DIST region @0x1000.
*/
static void subtest_dist_rdist(struct vm_gic *v)
{
int ret;
uint64_t addr;
+ struct vgic_region_attr rdist; /* CPU interface in GICv2*/
+ struct vgic_region_attr dist;
+
+ rdist = VGIC_DEV_IS_V3(v->gic_dev_type) ? gic_v3_redist_region
+ : gic_v2_cpu_region;
+ dist = VGIC_DEV_IS_V3(v->gic_dev_type) ? gic_v3_dist_region
+ : gic_v2_dist_region;
/* Check existing group/attributes */
kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
- KVM_VGIC_V3_ADDR_TYPE_DIST);
+ dist.attr);
kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
- KVM_VGIC_V3_ADDR_TYPE_REDIST);
+ rdist.attr);
/* check non existing attribute */
- ret = _kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, 0);
+ ret = _kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, -1);
TEST_ASSERT(ret && errno == ENXIO, "attribute not supported");
/* misaligned DIST and REDIST address settings */
- addr = 0x1000;
+ addr = dist.alignment / 0x10;
ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
- KVM_VGIC_V3_ADDR_TYPE_DIST, &addr, true);
- TEST_ASSERT(ret && errno == EINVAL, "GICv3 dist base not 64kB aligned");
+ dist.attr, &addr, true);
+ TEST_ASSERT(ret && errno == EINVAL, "GIC dist base not aligned");
+ addr = rdist.alignment / 0x10;
ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
- KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
- TEST_ASSERT(ret && errno == EINVAL, "GICv3 redist base not 64kB aligned");
+ rdist.attr, &addr, true);
+ TEST_ASSERT(ret && errno == EINVAL, "GIC redist/cpu base not aligned");
/* out of range address */
- if (max_ipa_bits) {
- addr = 1ULL << max_ipa_bits;
- ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
- KVM_VGIC_V3_ADDR_TYPE_DIST, &addr, true);
- TEST_ASSERT(ret && errno == E2BIG, "dist address beyond IPA limit");
+ addr = max_phys_size;
+ ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ dist.attr, &addr, true);
+ TEST_ASSERT(ret && errno == E2BIG, "dist address beyond IPA limit");
- ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
- KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
- TEST_ASSERT(ret && errno == E2BIG, "redist address beyond IPA limit");
- }
+ ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ rdist.attr, &addr, true);
+ TEST_ASSERT(ret && errno == E2BIG, "redist address beyond IPA limit");
+
+ /* Space for half a rdist (a rdist is: 2 * rdist.alignment). */
+ addr = max_phys_size - dist.alignment;
+ ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ rdist.attr, &addr, true);
+ TEST_ASSERT(ret && errno == E2BIG,
+ "half of the redist is beyond IPA limit");
/* set REDIST base address @0x0*/
addr = 0x00000;
kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
- KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
+ rdist.attr, &addr, true);
/* Attempt to create a second legacy redistributor region */
addr = 0xE0000;
ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
- KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
- TEST_ASSERT(ret && errno == EEXIST, "GICv3 redist base set again");
+ rdist.attr, &addr, true);
+ TEST_ASSERT(ret && errno == EEXIST, "GIC redist base set again");
- /* Attempt to mix legacy and new redistributor regions */
- addr = REDIST_REGION_ATTR_ADDR(NR_VCPUS, 0x100000, 0, 0);
- ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
- KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
- TEST_ASSERT(ret && errno == EINVAL, "attempt to mix GICv3 REDIST and REDIST_REGION");
+ ret = _kvm_device_check_attr(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_V3_ADDR_TYPE_REDIST);
+ if (!ret) {
+ /* Attempt to mix legacy and new redistributor regions */
+ addr = REDIST_REGION_ATTR_ADDR(NR_VCPUS, 0x100000, 0, 0);
+ ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION,
+ &addr, true);
+ TEST_ASSERT(ret && errno == EINVAL,
+ "attempt to mix GICv3 REDIST and REDIST_REGION");
+ }
/*
* Set overlapping DIST / REDIST, cannot be detected here. Will be detected
* on first vcpu run instead.
*/
- addr = 3 * 2 * 0x10000;
- kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR, KVM_VGIC_V3_ADDR_TYPE_DIST,
- &addr, true);
+ addr = rdist.size - rdist.alignment;
+ kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ dist.attr, &addr, true);
}
/* Test the new REDIST region API */
-static void subtest_redist_regions(struct vm_gic *v)
+static void subtest_v3_redist_regions(struct vm_gic *v)
{
uint64_t addr, expected_addr;
int ret;
@@ -199,12 +254,19 @@ static void subtest_redist_regions(struct vm_gic *v)
kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
- addr = REDIST_REGION_ATTR_ADDR(1, 1ULL << max_ipa_bits, 0, 2);
+ addr = REDIST_REGION_ATTR_ADDR(1, max_phys_size, 0, 2);
ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
TEST_ASSERT(ret && errno == E2BIG,
"register redist region with base address beyond IPA range");
+ /* The last redist is above the pa range. */
+ addr = REDIST_REGION_ATTR_ADDR(2, max_phys_size - 0x30000, 0, 2);
+ ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
+ TEST_ASSERT(ret && errno == E2BIG,
+ "register redist region with top address beyond IPA range");
+
addr = 0x260000;
ret = _kvm_device_access(v->gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
@@ -249,13 +311,12 @@ static void subtest_redist_regions(struct vm_gic *v)
* VGIC KVM device is created and initialized before the secondary CPUs
* get created
*/
-static void test_vgic_then_vcpus(void)
+static void test_vgic_then_vcpus(uint32_t gic_dev_type)
{
struct vm_gic v;
int ret, i;
- v.vm = vm_create_default(0, 0, guest_code);
- v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+ v = vm_gic_create_with_vcpus(gic_dev_type, 1);
subtest_dist_rdist(&v);
@@ -270,12 +331,12 @@ static void test_vgic_then_vcpus(void)
}
/* All the VCPUs are created before the VGIC KVM device gets initialized */
-static void test_vcpus_then_vgic(void)
+static void test_vcpus_then_vgic(uint32_t gic_dev_type)
{
struct vm_gic v;
int ret;
- v = vm_gic_create();
+ v = vm_gic_create_with_vcpus(gic_dev_type, NR_VCPUS);
subtest_dist_rdist(&v);
@@ -285,15 +346,15 @@ static void test_vcpus_then_vgic(void)
vm_gic_destroy(&v);
}
-static void test_new_redist_regions(void)
+static void test_v3_new_redist_regions(void)
{
void *dummy = NULL;
struct vm_gic v;
uint64_t addr;
int ret;
- v = vm_gic_create();
- subtest_redist_regions(&v);
+ v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS);
+ subtest_v3_redist_regions(&v);
kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true);
@@ -303,8 +364,8 @@ static void test_new_redist_regions(void)
/* step2 */
- v = vm_gic_create();
- subtest_redist_regions(&v);
+ v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS);
+ subtest_v3_redist_regions(&v);
addr = REDIST_REGION_ATTR_ADDR(1, 0x280000, 0, 2);
kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
@@ -317,8 +378,8 @@ static void test_new_redist_regions(void)
/* step 3 */
- v = vm_gic_create();
- subtest_redist_regions(&v);
+ v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS);
+ subtest_v3_redist_regions(&v);
_kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, dummy, true);
@@ -338,7 +399,7 @@ static void test_new_redist_regions(void)
vm_gic_destroy(&v);
}
-static void test_typer_accesses(void)
+static void test_v3_typer_accesses(void)
{
struct vm_gic v;
uint64_t addr;
@@ -351,12 +412,12 @@ static void test_typer_accesses(void)
vm_vcpu_add_default(v.vm, 3, guest_code);
- ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
TEST_ASSERT(ret && errno == EINVAL, "attempting to read GICR_TYPER of non created vcpu");
vm_vcpu_add_default(v.vm, 1, guest_code);
- ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
TEST_ASSERT(ret && errno == EBUSY, "read GICR_TYPER before GIC initialized");
vm_vcpu_add_default(v.vm, 2, guest_code);
@@ -365,7 +426,7 @@ static void test_typer_accesses(void)
KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true);
for (i = 0; i < NR_VCPUS ; i++) {
- ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && !val, "read GICR_TYPER before rdist region setting");
}
@@ -374,10 +435,10 @@ static void test_typer_accesses(void)
KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
/* The 2 first rdists should be put there (vcpu 0 and 3) */
- ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && !val, "read typer of rdist #0");
- ret = access_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x310, "read typer of rdist #1");
addr = REDIST_REGION_ATTR_ADDR(10, 0x100000, 0, 1);
@@ -385,11 +446,11 @@ static void test_typer_accesses(void)
KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
TEST_ASSERT(ret && errno == EINVAL, "collision with previous rdist region");
- ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x100,
"no redist region attached to vcpu #1 yet, last cannot be returned");
- ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x200,
"no redist region attached to vcpu #2, last cannot be returned");
@@ -397,10 +458,10 @@ static void test_typer_accesses(void)
kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
- ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #1");
- ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x210,
"read typer of rdist #1, last properly returned");
@@ -417,7 +478,7 @@ static void test_typer_accesses(void)
* rdist region #2 @0x200000 2 rdist capacity
* rdists: 1, 2
*/
-static void test_last_bit_redist_regions(void)
+static void test_v3_last_bit_redist_regions(void)
{
uint32_t vcpuids[] = { 0, 3, 5, 4, 1, 2 };
struct vm_gic v;
@@ -444,29 +505,29 @@ static void test_last_bit_redist_regions(void)
kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &addr, true);
- ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x000, "read typer of rdist #0");
- ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #1");
- ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x200, "read typer of rdist #2");
- ret = access_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x310, "read typer of rdist #3");
- ret = access_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x500, "read typer of rdist #5");
- ret = access_redist_reg(v.gic_fd, 4, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 4, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x410, "read typer of rdist #4");
vm_gic_destroy(&v);
}
/* Test last bit with legacy region */
-static void test_last_bit_single_rdist(void)
+static void test_v3_last_bit_single_rdist(void)
{
uint32_t vcpuids[] = { 0, 3, 5, 4, 1, 2 };
struct vm_gic v;
@@ -485,28 +546,106 @@ static void test_last_bit_single_rdist(void)
kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
- ret = access_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 0, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x000, "read typer of rdist #0");
- ret = access_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 3, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x300, "read typer of rdist #1");
- ret = access_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 5, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x500, "read typer of rdist #2");
- ret = access_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 1, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x100, "read typer of rdist #3");
- ret = access_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
+ ret = access_v3_redist_reg(v.gic_fd, 2, GICR_TYPER, &val, false);
TEST_ASSERT(!ret && val == 0x210, "read typer of rdist #3");
vm_gic_destroy(&v);
}
-void test_kvm_device(void)
+/* Uses the legacy REDIST region API. */
+static void test_v3_redist_ipa_range_check_at_vcpu_run(void)
+{
+ struct vm_gic v;
+ int ret, i;
+ uint64_t addr;
+
+ v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, 1);
+
+ /* Set space for 3 redists, we have 1 vcpu, so this succeeds. */
+ addr = max_phys_size - (3 * 2 * 0x10000);
+ kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_V3_ADDR_TYPE_REDIST, &addr, true);
+
+ addr = 0x00000;
+ kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_V3_ADDR_TYPE_DIST, &addr, true);
+
+ /* Add the rest of the VCPUs */
+ for (i = 1; i < NR_VCPUS; ++i)
+ vm_vcpu_add_default(v.vm, i, guest_code);
+
+ kvm_device_access(v.gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+ KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true);
+
+ /* Attempt to run a vcpu without enough redist space. */
+ ret = run_vcpu(v.vm, 2);
+ TEST_ASSERT(ret && errno == EINVAL,
+ "redist base+size above PA range detected on 1st vcpu run");
+
+ vm_gic_destroy(&v);
+}
+
+static void test_v3_its_region(void)
+{
+ struct vm_gic v;
+ uint64_t addr;
+ int its_fd, ret;
+
+ v = vm_gic_create_with_vcpus(KVM_DEV_TYPE_ARM_VGIC_V3, NR_VCPUS);
+ its_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_ITS, false);
+
+ addr = 0x401000;
+ ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_ITS_ADDR_TYPE, &addr, true);
+ TEST_ASSERT(ret && errno == EINVAL,
+ "ITS region with misaligned address");
+
+ addr = max_phys_size;
+ ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_ITS_ADDR_TYPE, &addr, true);
+ TEST_ASSERT(ret && errno == E2BIG,
+ "register ITS region with base address beyond IPA range");
+
+ addr = max_phys_size - 0x10000;
+ ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_ITS_ADDR_TYPE, &addr, true);
+ TEST_ASSERT(ret && errno == E2BIG,
+ "Half of ITS region is beyond IPA range");
+
+ /* This one succeeds setting the ITS base */
+ addr = 0x400000;
+ kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_ITS_ADDR_TYPE, &addr, true);
+
+ addr = 0x300000;
+ ret = _kvm_device_access(its_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_ITS_ADDR_TYPE, &addr, true);
+ TEST_ASSERT(ret && errno == EEXIST, "ITS base set again");
+
+ close(its_fd);
+ vm_gic_destroy(&v);
+}
+
+/*
+ * Returns 0 if it's possible to create GIC device of a given type (V2 or V3).
+ */
+int test_kvm_device(uint32_t gic_dev_type)
{
struct vm_gic v;
int ret, fd;
+ uint32_t other;
v.vm = vm_create_default_with_vcpus(NR_VCPUS, 0, 0, guest_code, NULL);
@@ -514,38 +653,70 @@ void test_kvm_device(void)
ret = _kvm_create_device(v.vm, 0, true, &fd);
TEST_ASSERT(ret && errno == ENODEV, "unsupported device");
- /* trial mode with VGIC_V3 device */
- ret = _kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, true, &fd);
- if (ret) {
- print_skip("GICv3 not supported");
- exit(KSFT_SKIP);
- }
- v.gic_fd = kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+ /* trial mode */
+ ret = _kvm_create_device(v.vm, gic_dev_type, true, &fd);
+ if (ret)
+ return ret;
+ v.gic_fd = kvm_create_device(v.vm, gic_dev_type, false);
+
+ ret = _kvm_create_device(v.vm, gic_dev_type, false, &fd);
+ TEST_ASSERT(ret && errno == EEXIST, "create GIC device twice");
- ret = _kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, false, &fd);
- TEST_ASSERT(ret && errno == EEXIST, "create GICv3 device twice");
+ kvm_create_device(v.vm, gic_dev_type, true);
- kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V3, true);
+ /* try to create the other gic_dev_type */
+ other = VGIC_DEV_IS_V2(gic_dev_type) ? KVM_DEV_TYPE_ARM_VGIC_V3
+ : KVM_DEV_TYPE_ARM_VGIC_V2;
- if (!_kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V2, true, &fd)) {
- ret = _kvm_create_device(v.vm, KVM_DEV_TYPE_ARM_VGIC_V2, false, &fd);
- TEST_ASSERT(ret && errno == EINVAL, "create GICv2 while v3 exists");
+ if (!_kvm_create_device(v.vm, other, true, &fd)) {
+ ret = _kvm_create_device(v.vm, other, false, &fd);
+ TEST_ASSERT(ret && errno == EINVAL,
+ "create GIC device while other version exists");
}
vm_gic_destroy(&v);
+
+ return 0;
+}
+
+void run_tests(uint32_t gic_dev_type)
+{
+ test_vcpus_then_vgic(gic_dev_type);
+ test_vgic_then_vcpus(gic_dev_type);
+
+ if (VGIC_DEV_IS_V3(gic_dev_type)) {
+ test_v3_new_redist_regions();
+ test_v3_typer_accesses();
+ test_v3_last_bit_redist_regions();
+ test_v3_last_bit_single_rdist();
+ test_v3_redist_ipa_range_check_at_vcpu_run();
+ test_v3_its_region();
+ }
}
int main(int ac, char **av)
{
- max_ipa_bits = kvm_check_cap(KVM_CAP_ARM_VM_IPA_SIZE);
+ int ret;
+ int pa_bits;
+
+ pa_bits = vm_guest_mode_params[VM_MODE_DEFAULT].pa_bits;
+ max_phys_size = 1ULL << pa_bits;
- test_kvm_device();
- test_vcpus_then_vgic();
- test_vgic_then_vcpus();
- test_new_redist_regions();
- test_typer_accesses();
- test_last_bit_redist_regions();
- test_last_bit_single_rdist();
+ ret = test_kvm_device(KVM_DEV_TYPE_ARM_VGIC_V3);
+ if (!ret) {
+ pr_info("Running GIC_v3 tests.\n");
+ run_tests(KVM_DEV_TYPE_ARM_VGIC_V3);
+ return 0;
+ }
+
+ ret = test_kvm_device(KVM_DEV_TYPE_ARM_VGIC_V2);
+ if (!ret) {
+ pr_info("Running GIC_v2 tests.\n");
+ run_tests(KVM_DEV_TYPE_ARM_VGIC_V2);
+ return 0;
+ }
+ print_skip("No GICv2 nor GICv3 support");
+ exit(KSFT_SKIP);
return 0;
}
diff --git a/tools/testing/selftests/kvm/include/aarch64/arch_timer.h b/tools/testing/selftests/kvm/include/aarch64/arch_timer.h
new file mode 100644
index 000000000000..cb7c03de3a21
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/arch_timer.h
@@ -0,0 +1,142 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM Generic Timer specific interface
+ */
+
+#ifndef SELFTEST_KVM_ARCH_TIMER_H
+#define SELFTEST_KVM_ARCH_TIMER_H
+
+#include "processor.h"
+
+enum arch_timer {
+ VIRTUAL,
+ PHYSICAL,
+};
+
+#define CTL_ENABLE (1 << 0)
+#define CTL_IMASK (1 << 1)
+#define CTL_ISTATUS (1 << 2)
+
+#define msec_to_cycles(msec) \
+ (timer_get_cntfrq() * (uint64_t)(msec) / 1000)
+
+#define usec_to_cycles(usec) \
+ (timer_get_cntfrq() * (uint64_t)(usec) / 1000000)
+
+#define cycles_to_usec(cycles) \
+ ((uint64_t)(cycles) * 1000000 / timer_get_cntfrq())
+
+static inline uint32_t timer_get_cntfrq(void)
+{
+ return read_sysreg(cntfrq_el0);
+}
+
+static inline uint64_t timer_get_cntct(enum arch_timer timer)
+{
+ isb();
+
+ switch (timer) {
+ case VIRTUAL:
+ return read_sysreg(cntvct_el0);
+ case PHYSICAL:
+ return read_sysreg(cntpct_el0);
+ default:
+ GUEST_ASSERT_1(0, timer);
+ }
+
+ /* We should not reach here */
+ return 0;
+}
+
+static inline void timer_set_cval(enum arch_timer timer, uint64_t cval)
+{
+ switch (timer) {
+ case VIRTUAL:
+ write_sysreg(cval, cntv_cval_el0);
+ break;
+ case PHYSICAL:
+ write_sysreg(cval, cntp_cval_el0);
+ break;
+ default:
+ GUEST_ASSERT_1(0, timer);
+ }
+
+ isb();
+}
+
+static inline uint64_t timer_get_cval(enum arch_timer timer)
+{
+ switch (timer) {
+ case VIRTUAL:
+ return read_sysreg(cntv_cval_el0);
+ case PHYSICAL:
+ return read_sysreg(cntp_cval_el0);
+ default:
+ GUEST_ASSERT_1(0, timer);
+ }
+
+ /* We should not reach here */
+ return 0;
+}
+
+static inline void timer_set_tval(enum arch_timer timer, uint32_t tval)
+{
+ switch (timer) {
+ case VIRTUAL:
+ write_sysreg(tval, cntv_tval_el0);
+ break;
+ case PHYSICAL:
+ write_sysreg(tval, cntp_tval_el0);
+ break;
+ default:
+ GUEST_ASSERT_1(0, timer);
+ }
+
+ isb();
+}
+
+static inline void timer_set_ctl(enum arch_timer timer, uint32_t ctl)
+{
+ switch (timer) {
+ case VIRTUAL:
+ write_sysreg(ctl, cntv_ctl_el0);
+ break;
+ case PHYSICAL:
+ write_sysreg(ctl, cntp_ctl_el0);
+ break;
+ default:
+ GUEST_ASSERT_1(0, timer);
+ }
+
+ isb();
+}
+
+static inline uint32_t timer_get_ctl(enum arch_timer timer)
+{
+ switch (timer) {
+ case VIRTUAL:
+ return read_sysreg(cntv_ctl_el0);
+ case PHYSICAL:
+ return read_sysreg(cntp_ctl_el0);
+ default:
+ GUEST_ASSERT_1(0, timer);
+ }
+
+ /* We should not reach here */
+ return 0;
+}
+
+static inline void timer_set_next_cval_ms(enum arch_timer timer, uint32_t msec)
+{
+ uint64_t now_ct = timer_get_cntct(timer);
+ uint64_t next_ct = now_ct + msec_to_cycles(msec);
+
+ timer_set_cval(timer, next_ct);
+}
+
+static inline void timer_set_next_tval_ms(enum arch_timer timer, uint32_t msec)
+{
+ timer_set_tval(timer, msec_to_cycles(msec));
+}
+
+#endif /* SELFTEST_KVM_ARCH_TIMER_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/delay.h b/tools/testing/selftests/kvm/include/aarch64/delay.h
new file mode 100644
index 000000000000..329e4f5079ea
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/delay.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM simple delay routines
+ */
+
+#ifndef SELFTEST_KVM_ARM_DELAY_H
+#define SELFTEST_KVM_ARM_DELAY_H
+
+#include "arch_timer.h"
+
+static inline void __delay(uint64_t cycles)
+{
+ enum arch_timer timer = VIRTUAL;
+ uint64_t start = timer_get_cntct(timer);
+
+ while ((timer_get_cntct(timer) - start) < cycles)
+ cpu_relax();
+}
+
+static inline void udelay(unsigned long usec)
+{
+ __delay(usec_to_cycles(usec));
+}
+
+#endif /* SELFTEST_KVM_ARM_DELAY_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/gic.h b/tools/testing/selftests/kvm/include/aarch64/gic.h
new file mode 100644
index 000000000000..85dd1e53048e
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/gic.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM Generic Interrupt Controller (GIC) specific defines
+ */
+
+#ifndef SELFTEST_KVM_GIC_H
+#define SELFTEST_KVM_GIC_H
+
+enum gic_type {
+ GIC_V3,
+ GIC_TYPE_MAX,
+};
+
+void gic_init(enum gic_type type, unsigned int nr_cpus,
+ void *dist_base, void *redist_base);
+void gic_irq_enable(unsigned int intid);
+void gic_irq_disable(unsigned int intid);
+unsigned int gic_get_and_ack_irq(void);
+void gic_set_eoi(unsigned int intid);
+
+#endif /* SELFTEST_KVM_GIC_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/aarch64/processor.h
index c0273aefa63d..27d8e1bb5b36 100644
--- a/tools/testing/selftests/kvm/include/aarch64/processor.h
+++ b/tools/testing/selftests/kvm/include/aarch64/processor.h
@@ -9,20 +9,24 @@
#include "kvm_util.h"
#include <linux/stringify.h>
+#include <linux/types.h>
+#include <asm/sysreg.h>
#define ARM64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \
KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x))
-#define CPACR_EL1 3, 0, 1, 0, 2
-#define TCR_EL1 3, 0, 2, 0, 2
-#define MAIR_EL1 3, 0, 10, 2, 0
-#define MPIDR_EL1 3, 0, 0, 0, 5
-#define TTBR0_EL1 3, 0, 2, 0, 0
-#define SCTLR_EL1 3, 0, 1, 0, 0
-#define VBAR_EL1 3, 0, 12, 0, 0
-
-#define ID_AA64DFR0_EL1 3, 0, 0, 5, 0
+/*
+ * KVM_ARM64_SYS_REG(sys_reg_id): Helper macro to convert
+ * SYS_* register definitions in asm/sysreg.h to use in KVM
+ * calls such as get_reg() and set_reg().
+ */
+#define KVM_ARM64_SYS_REG(sys_reg_id) \
+ ARM64_SYS_REG(sys_reg_Op0(sys_reg_id), \
+ sys_reg_Op1(sys_reg_id), \
+ sys_reg_CRn(sys_reg_id), \
+ sys_reg_CRm(sys_reg_id), \
+ sys_reg_Op2(sys_reg_id))
/*
* Default MAIR
@@ -59,7 +63,7 @@ static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id, uint
vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, &reg);
}
-void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *init);
+void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init *init);
void aarch64_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid,
struct kvm_vcpu_init *init, void *guest_code);
@@ -118,18 +122,64 @@ void vm_install_exception_handler(struct kvm_vm *vm,
void vm_install_sync_handler(struct kvm_vm *vm,
int vector, int ec, handler_fn handler);
-#define write_sysreg(reg, val) \
-({ \
- u64 __val = (u64)(val); \
- asm volatile("msr " __stringify(reg) ", %x0" : : "rZ" (__val)); \
-})
+static inline void cpu_relax(void)
+{
+ asm volatile("yield" ::: "memory");
+}
-#define read_sysreg(reg) \
-({ u64 val; \
- asm volatile("mrs %0, "__stringify(reg) : "=r"(val) : : "memory");\
- val; \
+#define isb() asm volatile("isb" : : : "memory")
+#define dsb(opt) asm volatile("dsb " #opt : : : "memory")
+#define dmb(opt) asm volatile("dmb " #opt : : : "memory")
+
+#define dma_wmb() dmb(oshst)
+#define __iowmb() dma_wmb()
+
+#define dma_rmb() dmb(oshld)
+
+#define __iormb(v) \
+({ \
+ unsigned long tmp; \
+ \
+ dma_rmb(); \
+ \
+ /* \
+ * Courtesy of arch/arm64/include/asm/io.h: \
+ * Create a dummy control dependency from the IO read to any \
+ * later instructions. This ensures that a subsequent call \
+ * to udelay() will be ordered due to the ISB in __delay(). \
+ */ \
+ asm volatile("eor %0, %1, %1\n" \
+ "cbnz %0, ." \
+ : "=r" (tmp) : "r" ((unsigned long)(v)) \
+ : "memory"); \
})
-#define isb() asm volatile("isb" : : : "memory")
+static __always_inline void __raw_writel(u32 val, volatile void *addr)
+{
+ asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr));
+}
+
+static __always_inline u32 __raw_readl(const volatile void *addr)
+{
+ u32 val;
+ asm volatile("ldr %w0, [%1]" : "=r" (val) : "r" (addr));
+ return val;
+}
+
+#define writel_relaxed(v,c) ((void)__raw_writel((__force u32)cpu_to_le32(v),(c)))
+#define readl_relaxed(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; })
+
+#define writel(v,c) ({ __iowmb(); writel_relaxed((v),(c));})
+#define readl(c) ({ u32 __v = readl_relaxed(c); __iormb(__v); __v; })
+
+static inline void local_irq_enable(void)
+{
+ asm volatile("msr daifclr, #3" : : : "memory");
+}
+
+static inline void local_irq_disable(void)
+{
+ asm volatile("msr daifset, #3" : : : "memory");
+}
#endif /* SELFTEST_KVM_PROCESSOR_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/spinlock.h b/tools/testing/selftests/kvm/include/aarch64/spinlock.h
new file mode 100644
index 000000000000..cf0984106d14
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/spinlock.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef SELFTEST_KVM_ARM64_SPINLOCK_H
+#define SELFTEST_KVM_ARM64_SPINLOCK_H
+
+struct spinlock {
+ int v;
+};
+
+extern void spin_lock(struct spinlock *lock);
+extern void spin_unlock(struct spinlock *lock);
+
+#endif /* SELFTEST_KVM_ARM64_SPINLOCK_H */
diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/aarch64/vgic.h
new file mode 100644
index 000000000000..0ecfb253893c
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/aarch64/vgic.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM Generic Interrupt Controller (GIC) host specific defines
+ */
+
+#ifndef SELFTEST_KVM_VGIC_H
+#define SELFTEST_KVM_VGIC_H
+
+#include <linux/kvm.h>
+
+#define REDIST_REGION_ATTR_ADDR(count, base, flags, index) \
+ (((uint64_t)(count) << 52) | \
+ ((uint64_t)((base) >> 16) << 16) | \
+ ((uint64_t)(flags) << 12) | \
+ index)
+
+int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus,
+ uint64_t gicd_base_gpa, uint64_t gicr_base_gpa);
+
+#endif /* SELFTEST_KVM_VGIC_H */
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 010b59b13917..bcf05f5381ed 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -400,4 +400,6 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc);
int vm_get_stats_fd(struct kvm_vm *vm);
int vcpu_get_stats_fd(struct kvm_vm *vm, uint32_t vcpuid);
+uint32_t guest_get_vcpuid(void);
+
#endif /* SELFTEST_KVM_UTIL_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic.c b/tools/testing/selftests/kvm/lib/aarch64/gic.c
new file mode 100644
index 000000000000..fff4fc27504d
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM Generic Interrupt Controller (GIC) support
+ */
+
+#include <errno.h>
+#include <linux/bits.h>
+#include <linux/sizes.h>
+
+#include "kvm_util.h"
+
+#include <gic.h>
+#include "gic_private.h"
+#include "processor.h"
+#include "spinlock.h"
+
+static const struct gic_common_ops *gic_common_ops;
+static struct spinlock gic_lock;
+
+static void gic_cpu_init(unsigned int cpu, void *redist_base)
+{
+ gic_common_ops->gic_cpu_init(cpu, redist_base);
+}
+
+static void
+gic_dist_init(enum gic_type type, unsigned int nr_cpus, void *dist_base)
+{
+ const struct gic_common_ops *gic_ops = NULL;
+
+ spin_lock(&gic_lock);
+
+ /* Distributor initialization is needed only once per VM */
+ if (gic_common_ops) {
+ spin_unlock(&gic_lock);
+ return;
+ }
+
+ if (type == GIC_V3)
+ gic_ops = &gicv3_ops;
+
+ GUEST_ASSERT(gic_ops);
+
+ gic_ops->gic_init(nr_cpus, dist_base);
+ gic_common_ops = gic_ops;
+
+ /* Make sure that the initialized data is visible to all the vCPUs */
+ dsb(sy);
+
+ spin_unlock(&gic_lock);
+}
+
+void gic_init(enum gic_type type, unsigned int nr_cpus,
+ void *dist_base, void *redist_base)
+{
+ uint32_t cpu = guest_get_vcpuid();
+
+ GUEST_ASSERT(type < GIC_TYPE_MAX);
+ GUEST_ASSERT(dist_base);
+ GUEST_ASSERT(redist_base);
+ GUEST_ASSERT(nr_cpus);
+
+ gic_dist_init(type, nr_cpus, dist_base);
+ gic_cpu_init(cpu, redist_base);
+}
+
+void gic_irq_enable(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_enable(intid);
+}
+
+void gic_irq_disable(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_irq_disable(intid);
+}
+
+unsigned int gic_get_and_ack_irq(void)
+{
+ uint64_t irqstat;
+ unsigned int intid;
+
+ GUEST_ASSERT(gic_common_ops);
+
+ irqstat = gic_common_ops->gic_read_iar();
+ intid = irqstat & GENMASK(23, 0);
+
+ return intid;
+}
+
+void gic_set_eoi(unsigned int intid)
+{
+ GUEST_ASSERT(gic_common_ops);
+ gic_common_ops->gic_write_eoir(intid);
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
new file mode 100644
index 000000000000..d81d739433dc
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_private.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM Generic Interrupt Controller (GIC) private defines that's only
+ * shared among the GIC library code.
+ */
+
+#ifndef SELFTEST_KVM_GIC_PRIVATE_H
+#define SELFTEST_KVM_GIC_PRIVATE_H
+
+struct gic_common_ops {
+ void (*gic_init)(unsigned int nr_cpus, void *dist_base);
+ void (*gic_cpu_init)(unsigned int cpu, void *redist_base);
+ void (*gic_irq_enable)(unsigned int intid);
+ void (*gic_irq_disable)(unsigned int intid);
+ uint64_t (*gic_read_iar)(void);
+ void (*gic_write_eoir)(uint32_t irq);
+};
+
+extern const struct gic_common_ops gicv3_ops;
+
+#endif /* SELFTEST_KVM_GIC_PRIVATE_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
new file mode 100644
index 000000000000..2dbf3339b62e
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM Generic Interrupt Controller (GIC) v3 support
+ */
+
+#include <linux/sizes.h>
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "delay.h"
+
+#include "gic_v3.h"
+#include "gic_private.h"
+
+struct gicv3_data {
+ void *dist_base;
+ void *redist_base[GICV3_MAX_CPUS];
+ unsigned int nr_cpus;
+ unsigned int nr_spis;
+};
+
+#define sgi_base_from_redist(redist_base) (redist_base + SZ_64K)
+
+enum gicv3_intid_range {
+ SGI_RANGE,
+ PPI_RANGE,
+ SPI_RANGE,
+ INVALID_RANGE,
+};
+
+static struct gicv3_data gicv3_data;
+
+static void gicv3_gicd_wait_for_rwp(void)
+{
+ unsigned int count = 100000; /* 1s */
+
+ while (readl(gicv3_data.dist_base + GICD_CTLR) & GICD_CTLR_RWP) {
+ GUEST_ASSERT(count--);
+ udelay(10);
+ }
+}
+
+static void gicv3_gicr_wait_for_rwp(void *redist_base)
+{
+ unsigned int count = 100000; /* 1s */
+
+ while (readl(redist_base + GICR_CTLR) & GICR_CTLR_RWP) {
+ GUEST_ASSERT(count--);
+ udelay(10);
+ }
+}
+
+static enum gicv3_intid_range get_intid_range(unsigned int intid)
+{
+ switch (intid) {
+ case 0 ... 15:
+ return SGI_RANGE;
+ case 16 ... 31:
+ return PPI_RANGE;
+ case 32 ... 1019:
+ return SPI_RANGE;
+ }
+
+ /* We should not be reaching here */
+ GUEST_ASSERT(0);
+
+ return INVALID_RANGE;
+}
+
+static uint64_t gicv3_read_iar(void)
+{
+ uint64_t irqstat = read_sysreg_s(SYS_ICC_IAR1_EL1);
+
+ dsb(sy);
+ return irqstat;
+}
+
+static void gicv3_write_eoir(uint32_t irq)
+{
+ write_sysreg_s(irq, SYS_ICC_EOIR1_EL1);
+ isb();
+}
+
+static void
+gicv3_config_irq(unsigned int intid, unsigned int offset)
+{
+ uint32_t cpu = guest_get_vcpuid();
+ uint32_t mask = 1 << (intid % 32);
+ enum gicv3_intid_range intid_range = get_intid_range(intid);
+ void *reg;
+
+ /* We care about 'cpu' only for SGIs or PPIs */
+ if (intid_range == SGI_RANGE || intid_range == PPI_RANGE) {
+ GUEST_ASSERT(cpu < gicv3_data.nr_cpus);
+
+ reg = sgi_base_from_redist(gicv3_data.redist_base[cpu]) +
+ offset;
+ writel(mask, reg);
+ gicv3_gicr_wait_for_rwp(gicv3_data.redist_base[cpu]);
+ } else if (intid_range == SPI_RANGE) {
+ reg = gicv3_data.dist_base + offset + (intid / 32) * 4;
+ writel(mask, reg);
+ gicv3_gicd_wait_for_rwp();
+ } else {
+ GUEST_ASSERT(0);
+ }
+}
+
+static void gicv3_irq_enable(unsigned int intid)
+{
+ gicv3_config_irq(intid, GICD_ISENABLER);
+}
+
+static void gicv3_irq_disable(unsigned int intid)
+{
+ gicv3_config_irq(intid, GICD_ICENABLER);
+}
+
+static void gicv3_enable_redist(void *redist_base)
+{
+ uint32_t val = readl(redist_base + GICR_WAKER);
+ unsigned int count = 100000; /* 1s */
+
+ val &= ~GICR_WAKER_ProcessorSleep;
+ writel(val, redist_base + GICR_WAKER);
+
+ /* Wait until the processor is 'active' */
+ while (readl(redist_base + GICR_WAKER) & GICR_WAKER_ChildrenAsleep) {
+ GUEST_ASSERT(count--);
+ udelay(10);
+ }
+}
+
+static inline void *gicr_base_cpu(void *redist_base, uint32_t cpu)
+{
+ /* Align all the redistributors sequentially */
+ return redist_base + cpu * SZ_64K * 2;
+}
+
+static void gicv3_cpu_init(unsigned int cpu, void *redist_base)
+{
+ void *sgi_base;
+ unsigned int i;
+ void *redist_base_cpu;
+
+ GUEST_ASSERT(cpu < gicv3_data.nr_cpus);
+
+ redist_base_cpu = gicr_base_cpu(redist_base, cpu);
+ sgi_base = sgi_base_from_redist(redist_base_cpu);
+
+ gicv3_enable_redist(redist_base_cpu);
+
+ /*
+ * Mark all the SGI and PPI interrupts as non-secure Group-1.
+ * Also, deactivate and disable them.
+ */
+ writel(~0, sgi_base + GICR_IGROUPR0);
+ writel(~0, sgi_base + GICR_ICACTIVER0);
+ writel(~0, sgi_base + GICR_ICENABLER0);
+
+ /* Set a default priority for all the SGIs and PPIs */
+ for (i = 0; i < 32; i += 4)
+ writel(GICD_INT_DEF_PRI_X4,
+ sgi_base + GICR_IPRIORITYR0 + i);
+
+ gicv3_gicr_wait_for_rwp(redist_base_cpu);
+
+ /* Enable the GIC system register (ICC_*) access */
+ write_sysreg_s(read_sysreg_s(SYS_ICC_SRE_EL1) | ICC_SRE_EL1_SRE,
+ SYS_ICC_SRE_EL1);
+
+ /* Set a default priority threshold */
+ write_sysreg_s(ICC_PMR_DEF_PRIO, SYS_ICC_PMR_EL1);
+
+ /* Enable non-secure Group-1 interrupts */
+ write_sysreg_s(ICC_IGRPEN1_EL1_ENABLE, SYS_ICC_GRPEN1_EL1);
+
+ gicv3_data.redist_base[cpu] = redist_base_cpu;
+}
+
+static void gicv3_dist_init(void)
+{
+ void *dist_base = gicv3_data.dist_base;
+ unsigned int i;
+
+ /* Disable the distributor until we set things up */
+ writel(0, dist_base + GICD_CTLR);
+ gicv3_gicd_wait_for_rwp();
+
+ /*
+ * Mark all the SPI interrupts as non-secure Group-1.
+ * Also, deactivate and disable them.
+ */
+ for (i = 32; i < gicv3_data.nr_spis; i += 32) {
+ writel(~0, dist_base + GICD_IGROUPR + i / 8);
+ writel(~0, dist_base + GICD_ICACTIVER + i / 8);
+ writel(~0, dist_base + GICD_ICENABLER + i / 8);
+ }
+
+ /* Set a default priority for all the SPIs */
+ for (i = 32; i < gicv3_data.nr_spis; i += 4)
+ writel(GICD_INT_DEF_PRI_X4,
+ dist_base + GICD_IPRIORITYR + i);
+
+ /* Wait for the settings to sync-in */
+ gicv3_gicd_wait_for_rwp();
+
+ /* Finally, enable the distributor globally with ARE */
+ writel(GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A |
+ GICD_CTLR_ENABLE_G1, dist_base + GICD_CTLR);
+ gicv3_gicd_wait_for_rwp();
+}
+
+static void gicv3_init(unsigned int nr_cpus, void *dist_base)
+{
+ GUEST_ASSERT(nr_cpus <= GICV3_MAX_CPUS);
+
+ gicv3_data.nr_cpus = nr_cpus;
+ gicv3_data.dist_base = dist_base;
+ gicv3_data.nr_spis = GICD_TYPER_SPIS(
+ readl(gicv3_data.dist_base + GICD_TYPER));
+ if (gicv3_data.nr_spis > 1020)
+ gicv3_data.nr_spis = 1020;
+
+ /*
+ * Initialize only the distributor for now.
+ * The redistributor and CPU interfaces are initialized
+ * later for every PE.
+ */
+ gicv3_dist_init();
+}
+
+const struct gic_common_ops gicv3_ops = {
+ .gic_init = gicv3_init,
+ .gic_cpu_init = gicv3_cpu_init,
+ .gic_irq_enable = gicv3_irq_enable,
+ .gic_irq_disable = gicv3_irq_disable,
+ .gic_read_iar = gicv3_read_iar,
+ .gic_write_eoir = gicv3_write_eoir,
+};
diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.h b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.h
new file mode 100644
index 000000000000..b51536d469a6
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/gic_v3.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ARM Generic Interrupt Controller (GIC) v3 specific defines
+ */
+
+#ifndef SELFTEST_KVM_GICV3_H
+#define SELFTEST_KVM_GICV3_H
+
+#include <asm/sysreg.h>
+
+/*
+ * Distributor registers
+ */
+#define GICD_CTLR 0x0000
+#define GICD_TYPER 0x0004
+#define GICD_IGROUPR 0x0080
+#define GICD_ISENABLER 0x0100
+#define GICD_ICENABLER 0x0180
+#define GICD_ICACTIVER 0x0380
+#define GICD_IPRIORITYR 0x0400
+
+/*
+ * The assumption is that the guest runs in a non-secure mode.
+ * The following bits of GICD_CTLR are defined accordingly.
+ */
+#define GICD_CTLR_RWP (1U << 31)
+#define GICD_CTLR_nASSGIreq (1U << 8)
+#define GICD_CTLR_ARE_NS (1U << 4)
+#define GICD_CTLR_ENABLE_G1A (1U << 1)
+#define GICD_CTLR_ENABLE_G1 (1U << 0)
+
+#define GICD_TYPER_SPIS(typer) ((((typer) & 0x1f) + 1) * 32)
+#define GICD_INT_DEF_PRI_X4 0xa0a0a0a0
+
+/*
+ * Redistributor registers
+ */
+#define GICR_CTLR 0x000
+#define GICR_WAKER 0x014
+
+#define GICR_CTLR_RWP (1U << 3)
+
+#define GICR_WAKER_ProcessorSleep (1U << 1)
+#define GICR_WAKER_ChildrenAsleep (1U << 2)
+
+/*
+ * Redistributor registers, offsets from SGI base
+ */
+#define GICR_IGROUPR0 GICD_IGROUPR
+#define GICR_ISENABLER0 GICD_ISENABLER
+#define GICR_ICENABLER0 GICD_ICENABLER
+#define GICR_ICACTIVER0 GICD_ICACTIVER
+#define GICR_IPRIORITYR0 GICD_IPRIORITYR
+
+/* CPU interface registers */
+#define SYS_ICC_PMR_EL1 sys_reg(3, 0, 4, 6, 0)
+#define SYS_ICC_IAR1_EL1 sys_reg(3, 0, 12, 12, 0)
+#define SYS_ICC_EOIR1_EL1 sys_reg(3, 0, 12, 12, 1)
+#define SYS_ICC_SRE_EL1 sys_reg(3, 0, 12, 12, 5)
+#define SYS_ICC_GRPEN1_EL1 sys_reg(3, 0, 12, 12, 7)
+
+#define ICC_PMR_DEF_PRIO 0xf0
+
+#define ICC_SRE_EL1_SRE (1U << 0)
+
+#define ICC_IGRPEN1_EL1_ENABLE (1U << 0)
+
+#define GICV3_MAX_CPUS 512
+
+#endif /* SELFTEST_KVM_GICV3_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 632b74d6b3ca..b4eeeafd2a70 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -212,7 +212,7 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
}
}
-void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *init)
+void aarch64_vcpu_setup(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_vcpu_init *init)
{
struct kvm_vcpu_init default_init = { .target = -1, };
uint64_t sctlr_el1, tcr_el1;
@@ -232,10 +232,10 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini
* Enable FP/ASIMD to avoid trapping when accessing Q0-Q15
* registers, which the variable argument list macros do.
*/
- set_reg(vm, vcpuid, ARM64_SYS_REG(CPACR_EL1), 3 << 20);
+ set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_CPACR_EL1), 3 << 20);
- get_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), &sctlr_el1);
- get_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), &tcr_el1);
+ get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1);
+ get_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1);
switch (vm->mode) {
case VM_MODE_P52V48_4K:
@@ -273,10 +273,11 @@ void aarch64_vcpu_setup(struct kvm_vm *vm, int vcpuid, struct kvm_vcpu_init *ini
tcr_el1 |= (1 << 8) | (1 << 10) | (3 << 12);
tcr_el1 |= (64 - vm->va_bits) /* T0SZ */;
- set_reg(vm, vcpuid, ARM64_SYS_REG(SCTLR_EL1), sctlr_el1);
- set_reg(vm, vcpuid, ARM64_SYS_REG(TCR_EL1), tcr_el1);
- set_reg(vm, vcpuid, ARM64_SYS_REG(MAIR_EL1), DEFAULT_MAIR_EL1);
- set_reg(vm, vcpuid, ARM64_SYS_REG(TTBR0_EL1), vm->pgd);
+ set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), sctlr_el1);
+ set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TCR_EL1), tcr_el1);
+ set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_MAIR_EL1), DEFAULT_MAIR_EL1);
+ set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TTBR0_EL1), vm->pgd);
+ set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_TPIDR_EL1), vcpuid);
}
void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
@@ -362,7 +363,7 @@ void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid)
{
extern char vectors;
- set_reg(vm, vcpuid, ARM64_SYS_REG(VBAR_EL1), (uint64_t)&vectors);
+ set_reg(vm, vcpuid, KVM_ARM64_SYS_REG(SYS_VBAR_EL1), (uint64_t)&vectors);
}
void route_exception(struct ex_regs *regs, int vector)
@@ -426,3 +427,8 @@ void vm_install_exception_handler(struct kvm_vm *vm, int vector,
assert(vector < VECTOR_NUM);
handlers->exception_handlers[vector][0] = handler;
}
+
+uint32_t guest_get_vcpuid(void)
+{
+ return read_sysreg(tpidr_el1);
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/spinlock.c b/tools/testing/selftests/kvm/lib/aarch64/spinlock.c
new file mode 100644
index 000000000000..a076e780be5d
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/spinlock.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM64 Spinlock support
+ */
+#include <stdint.h>
+
+#include "spinlock.h"
+
+void spin_lock(struct spinlock *lock)
+{
+ int val, res;
+
+ asm volatile(
+ "1: ldaxr %w0, [%2]\n"
+ " cbnz %w0, 1b\n"
+ " mov %w0, #1\n"
+ " stxr %w1, %w0, [%2]\n"
+ " cbnz %w1, 1b\n"
+ : "=&r" (val), "=&r" (res)
+ : "r" (&lock->v)
+ : "memory");
+}
+
+void spin_unlock(struct spinlock *lock)
+{
+ asm volatile("stlr wzr, [%0]\n" : : "r" (&lock->v) : "memory");
+}
diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
new file mode 100644
index 000000000000..b9b271ff520d
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/aarch64/vgic.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ARM Generic Interrupt Controller (GIC) v3 host support
+ */
+
+#include <linux/kvm.h>
+#include <linux/sizes.h>
+#include <asm/kvm.h>
+
+#include "kvm_util.h"
+#include "../kvm_util_internal.h"
+#include "vgic.h"
+
+/*
+ * vGIC-v3 default host setup
+ *
+ * Input args:
+ * vm - KVM VM
+ * nr_vcpus - Number of vCPUs supported by this VM
+ * gicd_base_gpa - Guest Physical Address of the Distributor region
+ * gicr_base_gpa - Guest Physical Address of the Redistributor region
+ *
+ * Output args: None
+ *
+ * Return: GIC file-descriptor or negative error code upon failure
+ *
+ * The function creates a vGIC-v3 device and maps the distributor and
+ * redistributor regions of the guest. Since it depends on the number of
+ * vCPUs for the VM, it must be called after all the vCPUs have been created.
+ */
+int vgic_v3_setup(struct kvm_vm *vm, unsigned int nr_vcpus,
+ uint64_t gicd_base_gpa, uint64_t gicr_base_gpa)
+{
+ int gic_fd;
+ uint64_t redist_attr;
+ struct list_head *iter;
+ unsigned int nr_gic_pages, nr_vcpus_created = 0;
+
+ TEST_ASSERT(nr_vcpus, "Number of vCPUs cannot be empty\n");
+
+ /*
+ * Make sure that the caller is infact calling this
+ * function after all the vCPUs are added.
+ */
+ list_for_each(iter, &vm->vcpus)
+ nr_vcpus_created++;
+ TEST_ASSERT(nr_vcpus == nr_vcpus_created,
+ "Number of vCPUs requested (%u) doesn't match with the ones created for the VM (%u)\n",
+ nr_vcpus, nr_vcpus_created);
+
+ /* Distributor setup */
+ gic_fd = kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3, false);
+ kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_V3_ADDR_TYPE_DIST, &gicd_base_gpa, true);
+ nr_gic_pages = vm_calc_num_guest_pages(vm->mode, KVM_VGIC_V3_DIST_SIZE);
+ virt_map(vm, gicd_base_gpa, gicd_base_gpa, nr_gic_pages);
+
+ /* Redistributor setup */
+ redist_attr = REDIST_REGION_ATTR_ADDR(nr_vcpus, gicr_base_gpa, 0, 0);
+ kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_ADDR,
+ KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION, &redist_attr, true);
+ nr_gic_pages = vm_calc_num_guest_pages(vm->mode,
+ KVM_VGIC_V3_REDIST_SIZE * nr_vcpus);
+ virt_map(vm, gicr_base_gpa, gicr_base_gpa, nr_gic_pages);
+
+ kvm_device_access(gic_fd, KVM_DEV_ARM_VGIC_GRP_CTRL,
+ KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true);
+
+ return gic_fd;
+}